From 40afce9fb0bfd92149ed87fda8dd545a3caff64d Mon Sep 17 00:00:00 2001 From: jeffser Date: Sun, 22 Sep 2024 14:55:38 -0600 Subject: [PATCH] New models added to list --- src/available_models.json | 12444 ++++++++++++++----------- src/available_models_descriptions.py | 91 +- 2 files changed, 7077 insertions(+), 5458 deletions(-) diff --git a/src/available_models.json b/src/available_models.json index 9558675..3a2a621 100644 --- a/src/available_models.json +++ b/src/available_models.json @@ -144,11 +144,11 @@ "141\u202fGB" ], [ - "70b-instruct-q2_k", + "70b-instruct-q2_K", "26\u202fGB" ], [ - "70b-instruct-q2_K", + "70b-instruct-q2_k", "26\u202fGB" ], [ @@ -167,10 +167,6 @@ "70b-instruct-q4_0", "40\u202fGB" ], - [ - "70b-instruct-q4_1", - "44\u202fGB" - ], [ "70b-instruct-q4_K_S", "40\u202fGB" @@ -389,7 +385,7 @@ }, "gemma2": { "url": "https://ollama.com/library/gemma2", - "description": "Google Gemma 2 is a high-performing and efficient model by now available in three sizes: 2B, 9B, and 27B.", + "description": "Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.", "tags": [ [ "latest", @@ -771,205 +767,121 @@ "image": false, "author": "Google DeepMind" }, - "mistral-nemo": { - "url": "https://ollama.com/library/mistral-nemo", - "description": "A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.", + "qwen2.5": { + "url": "https://ollama.com/library/qwen2.5", + "description": "Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.", "tags": [ [ "latest", - "7.1\u202fGB" - ], - [ - "12b", - "7.1\u202fGB" - ], - [ - "12b-instruct-2407-fp16", - "25\u202fGB" - ], - [ - "12b-instruct-2407-q2_K", - "4.8\u202fGB" - ], - [ - "12b-instruct-2407-q3_K_S", - "5.5\u202fGB" - ], - [ - "12b-instruct-2407-q3_K_M", - "6.1\u202fGB" - ], - [ - "12b-instruct-2407-q3_K_L", - "6.6\u202fGB" - ], - [ - "12b-instruct-2407-q4_0", - "7.1\u202fGB" - ], - [ - "12b-instruct-2407-q4_1", - "7.8\u202fGB" - ], - [ - "12b-instruct-2407-q4_K_S", - "7.1\u202fGB" - ], - [ - "12b-instruct-2407-q4_K_M", - "7.5\u202fGB" - ], - [ - "12b-instruct-2407-q5_0", - "8.5\u202fGB" - ], - [ - "12b-instruct-2407-q5_1", - "9.2\u202fGB" - ], - [ - "12b-instruct-2407-q5_K_S", - "8.5\u202fGB" - ], - [ - "12b-instruct-2407-q5_K_M", - "8.7\u202fGB" - ], - [ - "12b-instruct-2407-q6_K", - "10\u202fGB" - ], - [ - "12b-instruct-2407-q8_0", - "13\u202fGB" - ] - ], - "image": false, - "author": "Mistral AI" - }, - "mistral-large": { - "url": "https://ollama.com/library/mistral-large", - "description": "Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and support for dozens of languages.", - "tags": [ - [ - "latest", - "69\u202fGB" - ], - [ - "123b", - "69\u202fGB" - ], - [ - "123b-instruct-2407-fp16", - "245\u202fGB" - ], - [ - "123b-instruct-2407-q2_K", - "45\u202fGB" - ], - [ - "123b-instruct-2407-q3_K_S", - "53\u202fGB" - ], - [ - "123b-instruct-2407-q3_K_M", - "59\u202fGB" - ], - [ - "123b-instruct-2407-q3_K_L", - "65\u202fGB" - ], - [ - "123b-instruct-2407-q4_0", - "69\u202fGB" - ], - [ - "123b-instruct-2407-q4_1", - "77\u202fGB" - ], - [ - "123b-instruct-2407-q4_K_S", - "70\u202fGB" - ], - [ - "123b-instruct-2407-q4_K_M", - "73\u202fGB" - ], - [ - "123b-instruct-2407-q5_0", - "84\u202fGB" - ], - [ - "123b-instruct-2407-q5_1", - "92\u202fGB" - ], - [ - "123b-instruct-2407-q5_K_S", - "84\u202fGB" - ], - [ - "123b-instruct-2407-q5_K_M", - "86\u202fGB" - ], - [ - "123b-instruct-2407-q6_K", - "101\u202fGB" - ], - [ - "123b-instruct-2407-q8_0", - "130\u202fGB" - ] - ], - "image": false, - "author": "Mistral AI" - }, - "qwen2": { - "url": "https://ollama.com/library/qwen2", - "description": "Qwen2 is a new series of large language models from Alibaba group", - "tags": [ - [ - "latest", - "4.4\u202fGB" + "4.7\u202fGB" ], [ "0.5b", - "352\u202fMB" + "398\u202fMB" ], [ "1.5b", - "935\u202fMB" + "986\u202fMB" + ], + [ + "3b", + "1.9\u202fGB" ], [ "7b", - "4.4\u202fGB" + "4.7\u202fGB" + ], + [ + "14b", + "9.0\u202fGB" + ], + [ + "32b", + "20\u202fGB" ], [ "72b", - "41\u202fGB" + "47\u202fGB" + ], + [ + "0.5b-base", + "398\u202fMB" ], [ "0.5b-instruct", - "352\u202fMB" + "398\u202fMB" ], [ "1.5b-instruct", - "935\u202fMB" + "986\u202fMB" + ], + [ + "3b-instruct", + "1.9\u202fGB" ], [ "7b-instruct", - "4.4\u202fGB" + "4.7\u202fGB" ], [ - "7b-text", - "4.4\u202fGB" + "14b-instruct", + "9.0\u202fGB" + ], + [ + "32b-instruct", + "20\u202fGB" ], [ "72b-instruct", - "41\u202fGB" + "47\u202fGB" ], [ - "72b-text", - "41\u202fGB" + "0.5b-base-q2_K", + "339\u202fMB" + ], + [ + "0.5b-base-q3_K_S", + "338\u202fMB" + ], + [ + "0.5b-base-q3_K_M", + "355\u202fMB" + ], + [ + "0.5b-base-q3_K_L", + "369\u202fMB" + ], + [ + "0.5b-base-q4_0", + "352\u202fMB" + ], + [ + "0.5b-base-q4_1", + "375\u202fMB" + ], + [ + "0.5b-base-q4_K_S", + "385\u202fMB" + ], + [ + "0.5b-base-q4_K_M", + "398\u202fMB" + ], + [ + "0.5b-base-q5_0", + "397\u202fMB" + ], + [ + "0.5b-base-q5_1", + "419\u202fMB" + ], + [ + "0.5b-base-q5_K_S", + "413\u202fMB" + ], + [ + "0.5b-base-q8_0", + "531\u202fMB" ], [ "0.5b-instruct-fp16", @@ -1091,6 +1003,66 @@ "1.5b-instruct-q8_0", "1.6\u202fGB" ], + [ + "3b-instruct-fp16", + "6.2\u202fGB" + ], + [ + "3b-instruct-q2_K", + "1.3\u202fGB" + ], + [ + "3b-instruct-q3_K_S", + "1.5\u202fGB" + ], + [ + "3b-instruct-q3_K_M", + "1.6\u202fGB" + ], + [ + "3b-instruct-q3_K_L", + "1.7\u202fGB" + ], + [ + "3b-instruct-q4_0", + "1.8\u202fGB" + ], + [ + "3b-instruct-q4_1", + "2.0\u202fGB" + ], + [ + "3b-instruct-q4_K_S", + "1.8\u202fGB" + ], + [ + "3b-instruct-q4_K_M", + "1.9\u202fGB" + ], + [ + "3b-instruct-q5_0", + "2.2\u202fGB" + ], + [ + "3b-instruct-q5_1", + "2.3\u202fGB" + ], + [ + "3b-instruct-q5_K_S", + "2.2\u202fGB" + ], + [ + "3b-instruct-q5_K_M", + "2.2\u202fGB" + ], + [ + "3b-instruct-q6_K", + "2.5\u202fGB" + ], + [ + "3b-instruct-q8_0", + "3.3\u202fGB" + ], [ "7b-instruct-fp16", "15\u202fGB" @@ -1152,48 +1124,124 @@ "8.1\u202fGB" ], [ - "7b-text-q2_K", - "3.0\u202fGB" + "14b-instruct-fp16", + "30\u202fGB" ], [ - "7b-text-q3_K_S", - "3.5\u202fGB" - ], - [ - "7b-text-q3_K_M", - "3.8\u202fGB" - ], - [ - "7b-text-q3_K_L", - "4.1\u202fGB" - ], - [ - "7b-text-q4_0", - "4.4\u202fGB" - ], - [ - "7b-text-q4_1", - "4.9\u202fGB" - ], - [ - "7b-text-q4_K_S", - "4.5\u202fGB" - ], - [ - "7b-text-q4_K_M", - "4.7\u202fGB" - ], - [ - "7b-text-q5_0", - "5.3\u202fGB" - ], - [ - "7b-text-q5_1", + "14b-instruct-q2_K", "5.8\u202fGB" ], [ - "7b-text-q8_0", - "8.1\u202fGB" + "14b-instruct-q3_K_S", + "6.7\u202fGB" + ], + [ + "14b-instruct-q3_K_M", + "7.3\u202fGB" + ], + [ + "14b-instruct-q3_K_L", + "7.9\u202fGB" + ], + [ + "14b-instruct-q4_0", + "8.5\u202fGB" + ], + [ + "14b-instruct-q4_1", + "9.4\u202fGB" + ], + [ + "14b-instruct-q4_K_S", + "8.6\u202fGB" + ], + [ + "14b-instruct-q4_K_M", + "9.0\u202fGB" + ], + [ + "14b-instruct-q5_0", + "10\u202fGB" + ], + [ + "14b-instruct-q5_1", + "11\u202fGB" + ], + [ + "14b-instruct-q5_K_S", + "10\u202fGB" + ], + [ + "14b-instruct-q5_K_M", + "11\u202fGB" + ], + [ + "14b-instruct-q6_K", + "12\u202fGB" + ], + [ + "14b-instruct-q8_0", + "16\u202fGB" + ], + [ + "32b-instruct-fp16", + "66\u202fGB" + ], + [ + "32b-instruct-q2_K", + "12\u202fGB" + ], + [ + "32b-instruct-q3_K_S", + "14\u202fGB" + ], + [ + "32b-instruct-q3_K_M", + "16\u202fGB" + ], + [ + "32b-instruct-q3_K_L", + "17\u202fGB" + ], + [ + "32b-instruct-q4_0", + "19\u202fGB" + ], + [ + "32b-instruct-q4_1", + "21\u202fGB" + ], + [ + "32b-instruct-q4_K_S", + "19\u202fGB" + ], + [ + "32b-instruct-q4_K_M", + "20\u202fGB" + ], + [ + "32b-instruct-q5_0", + "23\u202fGB" + ], + [ + "32b-instruct-q5_1", + "25\u202fGB" + ], + [ + "32b-instruct-q5_K_S", + "23\u202fGB" + ], + [ + "32b-instruct-q5_K_M", + "23\u202fGB" + ], + [ + "32b-instruct-q6_K", + "27\u202fGB" + ], + [ + "32b-instruct-q8_0", + "35\u202fGB" ], [ "72b-instruct-fp16", @@ -1254,71 +1302,315 @@ [ "72b-instruct-q8_0", "77\u202fGB" - ], - [ - "72b-text-fp16", - "145\u202fGB" - ], - [ - "72b-text-q2_K", - "30\u202fGB" - ], - [ - "72b-text-q3_K_S", - "34\u202fGB" - ], - [ - "72b-text-q3_K_M", - "38\u202fGB" - ], - [ - "72b-text-q3_K_L", - "40\u202fGB" - ], - [ - "72b-text-q4_0", - "41\u202fGB" - ], - [ - "72b-text-q4_1", - "46\u202fGB" - ], - [ - "72b-text-q4_K_S", - "44\u202fGB" - ], - [ - "72b-text-q4_K_M", - "47\u202fGB" - ], - [ - "72b-text-q5_0", - "50\u202fGB" - ], - [ - "72b-text-q5_1", - "55\u202fGB" - ], - [ - "72b-text-q5_K_S", - "51\u202fGB" - ], - [ - "72b-text-q5_K_M", - "54\u202fGB" - ], - [ - "72b-text-q6_K", - "64\u202fGB" - ], - [ - "72b-text-q8_0", - "77\u202fGB" ] ], "image": false, "author": "Alibaba" }, + "phi3.5": { + "url": "https://ollama.com/library/phi3.5", + "description": "A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger sized models.", + "tags": [ + [ + "latest", + "2.2\u202fGB" + ], + [ + "3.8b", + "2.2\u202fGB" + ], + [ + "3.8b-mini-instruct-fp16", + "7.6\u202fGB" + ], + [ + "3.8b-mini-instruct-q2_K", + "1.4\u202fGB" + ], + [ + "3.8b-mini-instruct-q3_K_S", + "1.7\u202fGB" + ], + [ + "3.8b-mini-instruct-q3_K_M", + "2.0\u202fGB" + ], + [ + "3.8b-mini-instruct-q3_K_L", + "2.1\u202fGB" + ], + [ + "3.8b-mini-instruct-q4_0", + "2.2\u202fGB" + ], + [ + "3.8b-mini-instruct-q4_1", + "2.4\u202fGB" + ], + [ + "3.8b-mini-instruct-q4_K_S", + "2.2\u202fGB" + ], + [ + "3.8b-mini-instruct-q4_K_M", + "2.4\u202fGB" + ], + [ + "3.8b-mini-instruct-q5_0", + "2.6\u202fGB" + ], + [ + "3.8b-mini-instruct-q5_1", + "2.9\u202fGB" + ], + [ + "3.8b-mini-instruct-q5_K_S", + "2.6\u202fGB" + ], + [ + "3.8b-mini-instruct-q5_K_M", + "2.8\u202fGB" + ], + [ + "3.8b-mini-instruct-q6_K", + "3.1\u202fGB" + ], + [ + "3.8b-mini-instruct-q8_0", + "4.1\u202fGB" + ] + ], + "image": false, + "author": "Microsoft" + }, + "nemotron-mini": { + "url": "https://ollama.com/library/nemotron-mini", + "description": "A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.", + "tags": [ + [ + "latest", + "2.7\u202fGB" + ], + [ + "4b", + "2.7\u202fGB" + ], + [ + "4b-instruct-fp16", + "8.4\u202fGB" + ], + [ + "4b-instruct-q2_K", + "1.9\u202fGB" + ], + [ + "4b-instruct-q3_K_S", + "2.1\u202fGB" + ], + [ + "4b-instruct-q3_K_M", + "2.3\u202fGB" + ], + [ + "4b-instruct-q3_K_L", + "2.5\u202fGB" + ], + [ + "4b-instruct-q4_0", + "2.6\u202fGB" + ], + [ + "4b-instruct-q4_1", + "2.8\u202fGB" + ], + [ + "4b-instruct-q4_K_S", + "2.6\u202fGB" + ], + [ + "4b-instruct-q4_K_M", + "2.7\u202fGB" + ], + [ + "4b-instruct-q5_0", + "3.0\u202fGB" + ], + [ + "4b-instruct-q5_1", + "3.2\u202fGB" + ], + [ + "4b-instruct-q5_K_S", + "3.0\u202fGB" + ], + [ + "4b-instruct-q5_K_M", + "3.1\u202fGB" + ], + [ + "4b-instruct-q6_K", + "3.4\u202fGB" + ], + [ + "4b-instruct-q8_0", + "4.5\u202fGB" + ] + ], + "image": false, + "author": "Nvidia" + }, + "mistral-small": { + "url": "https://ollama.com/library/mistral-small", + "description": "Mistral Small is a lightweight model designed for cost-effective use in tasks like translation and summarization.", + "tags": [ + [ + "latest", + "13\u202fGB" + ], + [ + "22b", + "13\u202fGB" + ], + [ + "22b-instruct-2409-fp16", + "44\u202fGB" + ], + [ + "22b-instruct-2409-q2_K", + "8.3\u202fGB" + ], + [ + "22b-instruct-2409-q3_K_S", + "9.6\u202fGB" + ], + [ + "22b-instruct-2409-q3_K_M", + "11\u202fGB" + ], + [ + "22b-instruct-2409-q3_K_L", + "12\u202fGB" + ], + [ + "22b-instruct-2409-q4_0", + "13\u202fGB" + ], + [ + "22b-instruct-2409-q4_1", + "14\u202fGB" + ], + [ + "22b-instruct-2409-q4_K_S", + "13\u202fGB" + ], + [ + "22b-instruct-2409-q4_K_M", + "13\u202fGB" + ], + [ + "22b-instruct-2409-q5_0", + "15\u202fGB" + ], + [ + "22b-instruct-2409-q5_1", + "17\u202fGB" + ], + [ + "22b-instruct-2409-q5_K_S", + "15\u202fGB" + ], + [ + "22b-instruct-2409-q5_K_M", + "16\u202fGB" + ], + [ + "22b-instruct-2409-q6_K", + "18\u202fGB" + ], + [ + "22b-instruct-2409-q8_0", + "24\u202fGB" + ] + ], + "image": false, + "author": "Mistral AI" + }, + "mistral-nemo": { + "url": "https://ollama.com/library/mistral-nemo", + "description": "A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.", + "tags": [ + [ + "latest", + "7.1\u202fGB" + ], + [ + "12b", + "7.1\u202fGB" + ], + [ + "12b-instruct-2407-fp16", + "25\u202fGB" + ], + [ + "12b-instruct-2407-q2_K", + "4.8\u202fGB" + ], + [ + "12b-instruct-2407-q3_K_S", + "5.5\u202fGB" + ], + [ + "12b-instruct-2407-q3_K_M", + "6.1\u202fGB" + ], + [ + "12b-instruct-2407-q3_K_L", + "6.6\u202fGB" + ], + [ + "12b-instruct-2407-q4_0", + "7.1\u202fGB" + ], + [ + "12b-instruct-2407-q4_1", + "7.8\u202fGB" + ], + [ + "12b-instruct-2407-q4_K_S", + "7.1\u202fGB" + ], + [ + "12b-instruct-2407-q4_K_M", + "7.5\u202fGB" + ], + [ + "12b-instruct-2407-q5_0", + "8.5\u202fGB" + ], + [ + "12b-instruct-2407-q5_1", + "9.2\u202fGB" + ], + [ + "12b-instruct-2407-q5_K_S", + "8.5\u202fGB" + ], + [ + "12b-instruct-2407-q5_K_M", + "8.7\u202fGB" + ], + [ + "12b-instruct-2407-q6_K", + "10\u202fGB" + ], + [ + "12b-instruct-2407-q8_0", + "13\u202fGB" + ] + ], + "image": false, + "author": "Mistral AI" + }, "deepseek-coder-v2": { "url": "https://ollama.com/library/deepseek-coder-v2", "description": "An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.", @@ -1459,6 +1751,66 @@ "16b-lite-instruct-q8_0", "17\u202fGB" ], + [ + "236b-base-fp16", + "472\u202fGB" + ], + [ + "236b-base-q2_K", + "86\u202fGB" + ], + [ + "236b-base-q3_K_S", + "102\u202fGB" + ], + [ + "236b-base-q3_K_M", + "113\u202fGB" + ], + [ + "236b-base-q3_K_L", + "122\u202fGB" + ], + [ + "236b-base-q4_0", + "133\u202fGB" + ], + [ + "236b-base-q4_1", + "148\u202fGB" + ], + [ + "236b-base-q4_K_S", + "134\u202fGB" + ], + [ + "236b-base-q4_K_M", + "142\u202fGB" + ], + [ + "236b-base-q5_0", + "162\u202fGB" + ], + [ + "236b-base-q5_1", + "177\u202fGB" + ], + [ + "236b-base-q5_K_S", + "162\u202fGB" + ], + [ + "236b-base-q5_K_M", + "167\u202fGB" + ], + [ + "236b-base-q6_K", + "194\u202fGB" + ], + [ + "236b-base-q8_0", + "251\u202fGB" + ], [ "236b-instruct-fp16", "472\u202fGB" @@ -1492,11 +1844,11 @@ "134\u202fGB" ], [ - "236b-instruct-q4_K_M", + "236b-instruct-q4_k_m", "142\u202fGB" ], [ - "236b-instruct-q4_k_m", + "236b-instruct-q4_K_M", "142\u202fGB" ], [ @@ -1527,302 +1879,6 @@ "image": false, "author": "DeepSeek Team" }, - "phi3": { - "url": "https://ollama.com/library/phi3", - "description": "Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft.", - "tags": [ - [ - "latest", - "2.2\u202fGB" - ], - [ - "3.8b", - "2.2\u202fGB" - ], - [ - "14b", - "7.9\u202fGB" - ], - [ - "instruct", - "2.2\u202fGB" - ], - [ - "medium", - "7.9\u202fGB" - ], - [ - "medium-128k", - "7.9\u202fGB" - ], - [ - "medium-4k", - "7.9\u202fGB" - ], - [ - "mini", - "2.2\u202fGB" - ], - [ - "mini-128k", - "2.2\u202fGB" - ], - [ - "mini-4k", - "2.4\u202fGB" - ], - [ - "3.8b-instruct", - "2.2\u202fGB" - ], - [ - "14b-instruct", - "7.9\u202fGB" - ], - [ - "3.8b-mini-128k-instruct-fp16", - "7.6\u202fGB" - ], - [ - "3.8b-mini-128k-instruct-q2_K", - "1.4\u202fGB" - ], - [ - "3.8b-mini-128k-instruct-q3_K_S", - "1.7\u202fGB" - ], - [ - "3.8b-mini-128k-instruct-q3_K_M", - "2.0\u202fGB" - ], - [ - "3.8b-mini-128k-instruct-q3_K_L", - "2.1\u202fGB" - ], - [ - "3.8b-mini-128k-instruct-q4_0", - "2.2\u202fGB" - ], - [ - "3.8b-mini-128k-instruct-q4_1", - "2.4\u202fGB" - ], - [ - "3.8b-mini-128k-instruct-q4_K_S", - "2.2\u202fGB" - ], - [ - "3.8b-mini-128k-instruct-q4_K_M", - "2.4\u202fGB" - ], - [ - "3.8b-mini-128k-instruct-q5_0", - "2.6\u202fGB" - ], - [ - "3.8b-mini-128k-instruct-q5_1", - "2.9\u202fGB" - ], - [ - "3.8b-mini-128k-instruct-q5_K_S", - "2.6\u202fGB" - ], - [ - "3.8b-mini-128k-instruct-q5_K_M", - "2.8\u202fGB" - ], - [ - "3.8b-mini-128k-instruct-q6_K", - "3.1\u202fGB" - ], - [ - "3.8b-mini-128k-instruct-q8_0", - "4.1\u202fGB" - ], - [ - "3.8b-mini-4k-instruct-fp16", - "7.6\u202fGB" - ], - [ - "3.8b-mini-4k-instruct-q2_K", - "1.4\u202fGB" - ], - [ - "3.8b-mini-4k-instruct-q3_K_S", - "1.7\u202fGB" - ], - [ - "3.8b-mini-4k-instruct-q3_K_M", - "2.0\u202fGB" - ], - [ - "3.8b-mini-4k-instruct-q3_K_L", - "2.1\u202fGB" - ], - [ - "3.8b-mini-4k-instruct-q4_0", - "2.2\u202fGB" - ], - [ - "3.8b-mini-4k-instruct-q4_1", - "2.4\u202fGB" - ], - [ - "3.8b-mini-4k-instruct-q4_K_S", - "2.2\u202fGB" - ], - [ - "3.8b-mini-4k-instruct-q4_K_M", - "2.4\u202fGB" - ], - [ - "3.8b-mini-4k-instruct-q5_0", - "2.6\u202fGB" - ], - [ - "3.8b-mini-4k-instruct-q5_1", - "2.9\u202fGB" - ], - [ - "3.8b-mini-4k-instruct-q5_K_S", - "2.6\u202fGB" - ], - [ - "3.8b-mini-4k-instruct-q5_K_M", - "2.8\u202fGB" - ], - [ - "3.8b-mini-4k-instruct-q6_K", - "3.1\u202fGB" - ], - [ - "3.8b-mini-4k-instruct-q8_0", - "4.1\u202fGB" - ], - [ - "14b-medium-128k-instruct-fp16", - "28\u202fGB" - ], - [ - "14b-medium-128k-instruct-q2_K", - "5.1\u202fGB" - ], - [ - "14b-medium-128k-instruct-q3_K_S", - "6.1\u202fGB" - ], - [ - "14b-medium-128k-instruct-q3_K_M", - "6.9\u202fGB" - ], - [ - "14b-medium-128k-instruct-q3_K_L", - "7.5\u202fGB" - ], - [ - "14b-medium-128k-instruct-q4_0", - "7.9\u202fGB" - ], - [ - "14b-medium-128k-instruct-q4_1", - "8.8\u202fGB" - ], - [ - "14b-medium-128k-instruct-q4_K_S", - "8.0\u202fGB" - ], - [ - "14b-medium-128k-instruct-q4_K_M", - "8.6\u202fGB" - ], - [ - "14b-medium-128k-instruct-q5_0", - "9.6\u202fGB" - ], - [ - "14b-medium-128k-instruct-q5_1", - "10\u202fGB" - ], - [ - "14b-medium-128k-instruct-q5_K_S", - "9.6\u202fGB" - ], - [ - "14b-medium-128k-instruct-q5_K_M", - "10\u202fGB" - ], - [ - "14b-medium-128k-instruct-q6_K", - "11\u202fGB" - ], - [ - "14b-medium-128k-instruct-q8_0", - "15\u202fGB" - ], - [ - "14b-medium-4k-instruct-fp16", - "28\u202fGB" - ], - [ - "14b-medium-4k-instruct-q2_K", - "5.1\u202fGB" - ], - [ - "14b-medium-4k-instruct-q3_K_S", - "6.1\u202fGB" - ], - [ - "14b-medium-4k-instruct-q3_K_M", - "6.9\u202fGB" - ], - [ - "14b-medium-4k-instruct-q3_K_L", - "7.5\u202fGB" - ], - [ - "14b-medium-4k-instruct-q4_0", - "7.9\u202fGB" - ], - [ - "14b-medium-4k-instruct-q4_1", - "8.8\u202fGB" - ], - [ - "14b-medium-4k-instruct-q4_K_S", - "8.0\u202fGB" - ], - [ - "14b-medium-4k-instruct-q4_K_M", - "8.6\u202fGB" - ], - [ - "14b-medium-4k-instruct-q5_0", - "9.6\u202fGB" - ], - [ - "14b-medium-4k-instruct-q5_1", - "10\u202fGB" - ], - [ - "14b-medium-4k-instruct-q5_K_S", - "9.6\u202fGB" - ], - [ - "14b-medium-4k-instruct-q5_K_M", - "10\u202fGB" - ], - [ - "14b-medium-4k-instruct-q6_K", - "11\u202fGB" - ], - [ - "14b-medium-4k-instruct-q8_0", - "15\u202fGB" - ] - ], - "image": false, - "author": "Microsoft" - }, "mistral": { "url": "https://ollama.com/library/mistral", "description": "The 7B model released by Mistral AI, updated to version 0.3.", @@ -5647,6 +5703,698 @@ "image": false, "author": "Alibaba" }, + "qwen2": { + "url": "https://ollama.com/library/qwen2", + "description": "Qwen2 is a new series of large language models from Alibaba group", + "tags": [ + [ + "latest", + "4.4\u202fGB" + ], + [ + "0.5b", + "352\u202fMB" + ], + [ + "1.5b", + "935\u202fMB" + ], + [ + "7b", + "4.4\u202fGB" + ], + [ + "72b", + "41\u202fGB" + ], + [ + "0.5b-instruct", + "352\u202fMB" + ], + [ + "1.5b-instruct", + "935\u202fMB" + ], + [ + "7b-instruct", + "4.4\u202fGB" + ], + [ + "7b-text", + "4.4\u202fGB" + ], + [ + "72b-instruct", + "41\u202fGB" + ], + [ + "72b-text", + "41\u202fGB" + ], + [ + "0.5b-instruct-fp16", + "994\u202fMB" + ], + [ + "0.5b-instruct-q2_K", + "339\u202fMB" + ], + [ + "0.5b-instruct-q3_K_S", + "338\u202fMB" + ], + [ + "0.5b-instruct-q3_K_M", + "355\u202fMB" + ], + [ + "0.5b-instruct-q3_K_L", + "369\u202fMB" + ], + [ + "0.5b-instruct-q4_0", + "352\u202fMB" + ], + [ + "0.5b-instruct-q4_1", + "375\u202fMB" + ], + [ + "0.5b-instruct-q4_K_S", + "385\u202fMB" + ], + [ + "0.5b-instruct-q4_K_M", + "398\u202fMB" + ], + [ + "0.5b-instruct-q5_0", + "397\u202fMB" + ], + [ + "0.5b-instruct-q5_1", + "419\u202fMB" + ], + [ + "0.5b-instruct-q5_K_S", + "413\u202fMB" + ], + [ + "0.5b-instruct-q5_K_M", + "420\u202fMB" + ], + [ + "0.5b-instruct-q6_K", + "506\u202fMB" + ], + [ + "0.5b-instruct-q8_0", + "531\u202fMB" + ], + [ + "1.5b-instruct-fp16", + "3.1\u202fGB" + ], + [ + "1.5b-instruct-q2_K", + "676\u202fMB" + ], + [ + "1.5b-instruct-q3_K_S", + "761\u202fMB" + ], + [ + "1.5b-instruct-q3_K_M", + "824\u202fMB" + ], + [ + "1.5b-instruct-q3_K_L", + "880\u202fMB" + ], + [ + "1.5b-instruct-q4_0", + "935\u202fMB" + ], + [ + "1.5b-instruct-q4_1", + "1.0\u202fGB" + ], + [ + "1.5b-instruct-q4_K_S", + "940\u202fMB" + ], + [ + "1.5b-instruct-q4_K_M", + "986\u202fMB" + ], + [ + "1.5b-instruct-q5_0", + "1.1\u202fGB" + ], + [ + "1.5b-instruct-q5_1", + "1.2\u202fGB" + ], + [ + "1.5b-instruct-q5_K_S", + "1.1\u202fGB" + ], + [ + "1.5b-instruct-q5_K_M", + "1.1\u202fGB" + ], + [ + "1.5b-instruct-q6_K", + "1.3\u202fGB" + ], + [ + "1.5b-instruct-q8_0", + "1.6\u202fGB" + ], + [ + "7b-instruct-fp16", + "15\u202fGB" + ], + [ + "7b-instruct-q2_K", + "3.0\u202fGB" + ], + [ + "7b-instruct-q3_K_S", + "3.5\u202fGB" + ], + [ + "7b-instruct-q3_K_M", + "3.8\u202fGB" + ], + [ + "7b-instruct-q3_K_L", + "4.1\u202fGB" + ], + [ + "7b-instruct-q4_0", + "4.4\u202fGB" + ], + [ + "7b-instruct-q4_1", + "4.9\u202fGB" + ], + [ + "7b-instruct-q4_K_S", + "4.5\u202fGB" + ], + [ + "7b-instruct-q4_K_M", + "4.7\u202fGB" + ], + [ + "7b-instruct-q5_0", + "5.3\u202fGB" + ], + [ + "7b-instruct-q5_1", + "5.8\u202fGB" + ], + [ + "7b-instruct-q5_K_S", + "5.3\u202fGB" + ], + [ + "7b-instruct-q5_K_M", + "5.4\u202fGB" + ], + [ + "7b-instruct-q6_K", + "6.3\u202fGB" + ], + [ + "7b-instruct-q8_0", + "8.1\u202fGB" + ], + [ + "7b-text-q2_K", + "3.0\u202fGB" + ], + [ + "7b-text-q3_K_S", + "3.5\u202fGB" + ], + [ + "7b-text-q3_K_M", + "3.8\u202fGB" + ], + [ + "7b-text-q3_K_L", + "4.1\u202fGB" + ], + [ + "7b-text-q4_0", + "4.4\u202fGB" + ], + [ + "7b-text-q4_1", + "4.9\u202fGB" + ], + [ + "7b-text-q4_K_S", + "4.5\u202fGB" + ], + [ + "7b-text-q4_K_M", + "4.7\u202fGB" + ], + [ + "7b-text-q5_0", + "5.3\u202fGB" + ], + [ + "7b-text-q5_1", + "5.8\u202fGB" + ], + [ + "7b-text-q8_0", + "8.1\u202fGB" + ], + [ + "72b-instruct-fp16", + "145\u202fGB" + ], + [ + "72b-instruct-q2_K", + "30\u202fGB" + ], + [ + "72b-instruct-q3_K_S", + "34\u202fGB" + ], + [ + "72b-instruct-q3_K_M", + "38\u202fGB" + ], + [ + "72b-instruct-q3_K_L", + "40\u202fGB" + ], + [ + "72b-instruct-q4_0", + "41\u202fGB" + ], + [ + "72b-instruct-q4_1", + "46\u202fGB" + ], + [ + "72b-instruct-q4_K_S", + "44\u202fGB" + ], + [ + "72b-instruct-q4_K_M", + "47\u202fGB" + ], + [ + "72b-instruct-q5_0", + "50\u202fGB" + ], + [ + "72b-instruct-q5_1", + "55\u202fGB" + ], + [ + "72b-instruct-q5_K_S", + "51\u202fGB" + ], + [ + "72b-instruct-q5_K_M", + "54\u202fGB" + ], + [ + "72b-instruct-q6_K", + "64\u202fGB" + ], + [ + "72b-instruct-q8_0", + "77\u202fGB" + ], + [ + "72b-text-fp16", + "145\u202fGB" + ], + [ + "72b-text-q2_K", + "30\u202fGB" + ], + [ + "72b-text-q3_K_S", + "34\u202fGB" + ], + [ + "72b-text-q3_K_M", + "38\u202fGB" + ], + [ + "72b-text-q3_K_L", + "40\u202fGB" + ], + [ + "72b-text-q4_0", + "41\u202fGB" + ], + [ + "72b-text-q4_1", + "46\u202fGB" + ], + [ + "72b-text-q4_K_S", + "44\u202fGB" + ], + [ + "72b-text-q4_K_M", + "47\u202fGB" + ], + [ + "72b-text-q5_0", + "50\u202fGB" + ], + [ + "72b-text-q5_1", + "55\u202fGB" + ], + [ + "72b-text-q5_K_S", + "51\u202fGB" + ], + [ + "72b-text-q5_K_M", + "54\u202fGB" + ], + [ + "72b-text-q6_K", + "64\u202fGB" + ], + [ + "72b-text-q8_0", + "77\u202fGB" + ] + ], + "image": false, + "author": "Alibaba" + }, + "phi3": { + "url": "https://ollama.com/library/phi3", + "description": "Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft.", + "tags": [ + [ + "latest", + "2.2\u202fGB" + ], + [ + "3.8b", + "2.2\u202fGB" + ], + [ + "14b", + "7.9\u202fGB" + ], + [ + "instruct", + "2.2\u202fGB" + ], + [ + "medium", + "7.9\u202fGB" + ], + [ + "medium-128k", + "7.9\u202fGB" + ], + [ + "medium-4k", + "7.9\u202fGB" + ], + [ + "mini", + "2.2\u202fGB" + ], + [ + "mini-128k", + "2.2\u202fGB" + ], + [ + "mini-4k", + "2.4\u202fGB" + ], + [ + "3.8b-instruct", + "2.2\u202fGB" + ], + [ + "14b-instruct", + "7.9\u202fGB" + ], + [ + "3.8b-mini-128k-instruct-fp16", + "7.6\u202fGB" + ], + [ + "3.8b-mini-128k-instruct-q2_K", + "1.4\u202fGB" + ], + [ + "3.8b-mini-128k-instruct-q3_K_S", + "1.7\u202fGB" + ], + [ + "3.8b-mini-128k-instruct-q3_K_M", + "2.0\u202fGB" + ], + [ + "3.8b-mini-128k-instruct-q3_K_L", + "2.1\u202fGB" + ], + [ + "3.8b-mini-128k-instruct-q4_0", + "2.2\u202fGB" + ], + [ + "3.8b-mini-128k-instruct-q4_1", + "2.4\u202fGB" + ], + [ + "3.8b-mini-128k-instruct-q4_K_S", + "2.2\u202fGB" + ], + [ + "3.8b-mini-128k-instruct-q4_K_M", + "2.4\u202fGB" + ], + [ + "3.8b-mini-128k-instruct-q5_0", + "2.6\u202fGB" + ], + [ + "3.8b-mini-128k-instruct-q5_1", + "2.9\u202fGB" + ], + [ + "3.8b-mini-128k-instruct-q5_K_S", + "2.6\u202fGB" + ], + [ + "3.8b-mini-128k-instruct-q5_K_M", + "2.8\u202fGB" + ], + [ + "3.8b-mini-128k-instruct-q6_K", + "3.1\u202fGB" + ], + [ + "3.8b-mini-128k-instruct-q8_0", + "4.1\u202fGB" + ], + [ + "3.8b-mini-4k-instruct-fp16", + "7.6\u202fGB" + ], + [ + "3.8b-mini-4k-instruct-q2_K", + "1.4\u202fGB" + ], + [ + "3.8b-mini-4k-instruct-q3_K_S", + "1.7\u202fGB" + ], + [ + "3.8b-mini-4k-instruct-q3_K_M", + "2.0\u202fGB" + ], + [ + "3.8b-mini-4k-instruct-q3_K_L", + "2.1\u202fGB" + ], + [ + "3.8b-mini-4k-instruct-q4_0", + "2.2\u202fGB" + ], + [ + "3.8b-mini-4k-instruct-q4_1", + "2.4\u202fGB" + ], + [ + "3.8b-mini-4k-instruct-q4_K_S", + "2.2\u202fGB" + ], + [ + "3.8b-mini-4k-instruct-q4_K_M", + "2.4\u202fGB" + ], + [ + "3.8b-mini-4k-instruct-q5_0", + "2.6\u202fGB" + ], + [ + "3.8b-mini-4k-instruct-q5_1", + "2.9\u202fGB" + ], + [ + "3.8b-mini-4k-instruct-q5_K_S", + "2.6\u202fGB" + ], + [ + "3.8b-mini-4k-instruct-q5_K_M", + "2.8\u202fGB" + ], + [ + "3.8b-mini-4k-instruct-q6_K", + "3.1\u202fGB" + ], + [ + "3.8b-mini-4k-instruct-q8_0", + "4.1\u202fGB" + ], + [ + "14b-medium-128k-instruct-fp16", + "28\u202fGB" + ], + [ + "14b-medium-128k-instruct-q2_K", + "5.1\u202fGB" + ], + [ + "14b-medium-128k-instruct-q3_K_S", + "6.1\u202fGB" + ], + [ + "14b-medium-128k-instruct-q3_K_M", + "6.9\u202fGB" + ], + [ + "14b-medium-128k-instruct-q3_K_L", + "7.5\u202fGB" + ], + [ + "14b-medium-128k-instruct-q4_0", + "7.9\u202fGB" + ], + [ + "14b-medium-128k-instruct-q4_1", + "8.8\u202fGB" + ], + [ + "14b-medium-128k-instruct-q4_K_S", + "8.0\u202fGB" + ], + [ + "14b-medium-128k-instruct-q4_K_M", + "8.6\u202fGB" + ], + [ + "14b-medium-128k-instruct-q5_0", + "9.6\u202fGB" + ], + [ + "14b-medium-128k-instruct-q5_1", + "10\u202fGB" + ], + [ + "14b-medium-128k-instruct-q5_K_S", + "9.6\u202fGB" + ], + [ + "14b-medium-128k-instruct-q5_K_M", + "10\u202fGB" + ], + [ + "14b-medium-128k-instruct-q6_K", + "11\u202fGB" + ], + [ + "14b-medium-128k-instruct-q8_0", + "15\u202fGB" + ], + [ + "14b-medium-4k-instruct-fp16", + "28\u202fGB" + ], + [ + "14b-medium-4k-instruct-q2_K", + "5.1\u202fGB" + ], + [ + "14b-medium-4k-instruct-q3_K_S", + "6.1\u202fGB" + ], + [ + "14b-medium-4k-instruct-q3_K_M", + "6.9\u202fGB" + ], + [ + "14b-medium-4k-instruct-q3_K_L", + "7.5\u202fGB" + ], + [ + "14b-medium-4k-instruct-q4_0", + "7.9\u202fGB" + ], + [ + "14b-medium-4k-instruct-q4_1", + "8.8\u202fGB" + ], + [ + "14b-medium-4k-instruct-q4_K_S", + "8.0\u202fGB" + ], + [ + "14b-medium-4k-instruct-q4_K_M", + "8.6\u202fGB" + ], + [ + "14b-medium-4k-instruct-q5_0", + "9.6\u202fGB" + ], + [ + "14b-medium-4k-instruct-q5_1", + "10\u202fGB" + ], + [ + "14b-medium-4k-instruct-q5_K_S", + "9.6\u202fGB" + ], + [ + "14b-medium-4k-instruct-q5_K_M", + "10\u202fGB" + ], + [ + "14b-medium-4k-instruct-q6_K", + "11\u202fGB" + ], + [ + "14b-medium-4k-instruct-q8_0", + "15\u202fGB" + ] + ], + "image": false, + "author": "Microsoft" + }, "llama2": { "url": "https://ollama.com/library/llama2", "description": "Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters.", @@ -7907,173 +8655,281 @@ "image": false, "author": "Mixedbread.ai" }, - "zephyr": { - "url": "https://ollama.com/library/zephyr", - "description": "Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants.", + "starcoder2": { + "url": "https://ollama.com/library/starcoder2", + "description": "StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.", "tags": [ [ "latest", - "4.1\u202fGB" + "1.7\u202fGB" + ], + [ + "3b", + "1.7\u202fGB" ], [ "7b", - "4.1\u202fGB" + "4.0\u202fGB" ], [ - "141b", - "80\u202fGB" + "15b", + "9.1\u202fGB" ], [ - "7b-alpha", - "4.1\u202fGB" + "instruct", + "9.1\u202fGB" ], [ - "7b-beta", - "4.1\u202fGB" + "15b-instruct", + "9.1\u202fGB" ], [ - "141b-v0.1", - "80\u202fGB" + "3b-fp16", + "6.1\u202fGB" ], [ - "7b-alpha-fp16", - "14\u202fGB" + "3b-q2_K", + "1.1\u202fGB" ], [ - "7b-alpha-q2_K", - "3.1\u202fGB" + "3b-q3_K_S", + "1.3\u202fGB" ], [ - "7b-alpha-q3_K_S", + "3b-q3_K_M", + "1.5\u202fGB" + ], + [ + "3b-q3_K_L", + "1.7\u202fGB" + ], + [ + "3b-q4_0", + "1.7\u202fGB" + ], + [ + "3b-q4_1", + "1.9\u202fGB" + ], + [ + "3b-q4_K_S", + "1.7\u202fGB" + ], + [ + "3b-q4_K_M", + "1.8\u202fGB" + ], + [ + "3b-q5_0", + "2.1\u202fGB" + ], + [ + "3b-q5_1", + "2.3\u202fGB" + ], + [ + "3b-q5_K_S", + "2.1\u202fGB" + ], + [ + "3b-q5_K_M", + "2.2\u202fGB" + ], + [ + "3b-q6_K", + "2.5\u202fGB" + ], + [ + "3b-q8_0", "3.2\u202fGB" ], [ - "7b-alpha-q3_K_M", - "3.5\u202fGB" - ], - [ - "7b-alpha-q3_K_L", - "3.8\u202fGB" - ], - [ - "7b-alpha-q4_0", - "4.1\u202fGB" - ], - [ - "7b-alpha-q4_1", - "4.6\u202fGB" - ], - [ - "7b-alpha-q4_K_S", - "4.1\u202fGB" - ], - [ - "7b-alpha-q4_K_M", - "4.4\u202fGB" - ], - [ - "7b-alpha-q5_0", - "5.0\u202fGB" - ], - [ - "7b-alpha-q5_1", - "5.4\u202fGB" - ], - [ - "7b-alpha-q5_K_S", - "5.0\u202fGB" - ], - [ - "7b-alpha-q5_K_M", - "5.1\u202fGB" - ], - [ - "7b-alpha-q6_K", - "5.9\u202fGB" - ], - [ - "7b-alpha-q8_0", - "7.7\u202fGB" - ], - [ - "7b-beta-fp16", + "7b-fp16", "14\u202fGB" ], [ - "7b-beta-q2_K", + "7b-q2_K", + "2.7\u202fGB" + ], + [ + "7b-q3_K_S", "3.1\u202fGB" ], [ - "7b-beta-q3_K_S", - "3.2\u202fGB" + "7b-q3_K_M", + "3.6\u202fGB" ], [ - "7b-beta-q3_K_M", - "3.5\u202fGB" + "7b-q3_K_L", + "4.0\u202fGB" ], [ - "7b-beta-q3_K_L", - "3.8\u202fGB" + "7b-q4_0", + "4.0\u202fGB" ], [ - "7b-beta-q4_0", + "7b-q4_1", + "4.5\u202fGB" + ], + [ + "7b-q4_K_S", "4.1\u202fGB" ], [ - "7b-beta-q4_1", - "4.6\u202fGB" - ], - [ - "7b-beta-q4_K_S", - "4.1\u202fGB" - ], - [ - "7b-beta-q4_K_M", + "7b-q4_K_M", "4.4\u202fGB" ], [ - "7b-beta-q5_0", - "5.0\u202fGB" + "7b-q5_0", + "4.9\u202fGB" ], [ - "7b-beta-q5_1", + "7b-q5_1", "5.4\u202fGB" ], [ - "7b-beta-q5_K_S", - "5.0\u202fGB" + "7b-q5_K_S", + "4.9\u202fGB" ], [ - "7b-beta-q5_K_M", + "7b-q5_K_M", "5.1\u202fGB" ], [ - "7b-beta-q6_K", + "7b-q6_K", "5.9\u202fGB" ], [ - "7b-beta-q8_0", - "7.7\u202fGB" + "7b-q8_0", + "7.6\u202fGB" ], [ - "141b-v0.1-fp16", - "281\u202fGB" + "15b-fp16", + "32\u202fGB" ], [ - "141b-v0.1-q2_K", - "52\u202fGB" + "15b-q2_K", + "6.2\u202fGB" ], [ - "141b-v0.1-q4_0", - "80\u202fGB" + "15b-q3_K_S", + "7.0\u202fGB" ], [ - "141b-v0.1-q8_0", - "149\u202fGB" + "15b-q3_K_M", + "8.1\u202fGB" + ], + [ + "15b-q3_K_L", + "9.0\u202fGB" + ], + [ + "15b-q4_0", + "9.1\u202fGB" + ], + [ + "15b-q4_1", + "10\u202fGB" + ], + [ + "15b-q4_K_S", + "9.3\u202fGB" + ], + [ + "15b-q4_K_M", + "9.9\u202fGB" + ], + [ + "15b-q5_0", + "11\u202fGB" + ], + [ + "15b-q5_1", + "12\u202fGB" + ], + [ + "15b-q5_K_S", + "11\u202fGB" + ], + [ + "15b-q5_K_M", + "11\u202fGB" + ], + [ + "15b-q6_K", + "13\u202fGB" + ], + [ + "15b-q8_0", + "17\u202fGB" + ], + [ + "15b-instruct-q4_0", + "9.1\u202fGB" + ], + [ + "15b-instruct-v0.1-fp16", + "32\u202fGB" + ], + [ + "15b-instruct-v0.1-q2_K", + "6.2\u202fGB" + ], + [ + "15b-instruct-v0.1-q3_K_S", + "7.0\u202fGB" + ], + [ + "15b-instruct-v0.1-q3_K_M", + "8.0\u202fGB" + ], + [ + "15b-instruct-v0.1-q3_K_L", + "9.0\u202fGB" + ], + [ + "15b-instruct-v0.1-q4_0", + "9.1\u202fGB" + ], + [ + "15b-instruct-v0.1-q4_1", + "10\u202fGB" + ], + [ + "15b-instruct-v0.1-q4_K_S", + "9.2\u202fGB" + ], + [ + "15b-instruct-v0.1-q4_K_M", + "9.9\u202fGB" + ], + [ + "15b-instruct-v0.1-q5_0", + "11\u202fGB" + ], + [ + "15b-instruct-v0.1-q5_1", + "12\u202fGB" + ], + [ + "15b-instruct-v0.1-q5_K_S", + "11\u202fGB" + ], + [ + "15b-instruct-v0.1-q5_K_M", + "11\u202fGB" + ], + [ + "15b-instruct-v0.1-q6_K", + "13\u202fGB" + ], + [ + "15b-instruct-v0.1-q8_0", + "17\u202fGB" ] ], "image": false, - "author": "Hugging Face H4" + "author": "BigCode" }, "dolphin-mistral": { "url": "https://ollama.com/library/dolphin-mistral", @@ -8563,281 +9419,393 @@ "image": false, "author": "Eric Hartford" }, - "starcoder2": { - "url": "https://ollama.com/library/starcoder2", - "description": "StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.", + "zephyr": { + "url": "https://ollama.com/library/zephyr", + "description": "Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants.", "tags": [ [ "latest", - "1.7\u202fGB" - ], - [ - "3b", - "1.7\u202fGB" - ], - [ - "7b", - "4.0\u202fGB" - ], - [ - "15b", - "9.1\u202fGB" - ], - [ - "instruct", - "9.1\u202fGB" - ], - [ - "15b-instruct", - "9.1\u202fGB" - ], - [ - "3b-fp16", - "6.1\u202fGB" - ], - [ - "3b-q2_K", - "1.1\u202fGB" - ], - [ - "3b-q3_K_S", - "1.3\u202fGB" - ], - [ - "3b-q3_K_M", - "1.5\u202fGB" - ], - [ - "3b-q3_K_L", - "1.7\u202fGB" - ], - [ - "3b-q4_0", - "1.7\u202fGB" - ], - [ - "3b-q4_1", - "1.9\u202fGB" - ], - [ - "3b-q4_K_S", - "1.7\u202fGB" - ], - [ - "3b-q4_K_M", - "1.8\u202fGB" - ], - [ - "3b-q5_0", - "2.1\u202fGB" - ], - [ - "3b-q5_1", - "2.3\u202fGB" - ], - [ - "3b-q5_K_S", - "2.1\u202fGB" - ], - [ - "3b-q5_K_M", - "2.2\u202fGB" - ], - [ - "3b-q6_K", - "2.5\u202fGB" - ], - [ - "3b-q8_0", - "3.2\u202fGB" - ], - [ - "7b-fp16", - "14\u202fGB" - ], - [ - "7b-q2_K", - "2.7\u202fGB" - ], - [ - "7b-q3_K_S", - "3.1\u202fGB" - ], - [ - "7b-q3_K_M", - "3.6\u202fGB" - ], - [ - "7b-q3_K_L", - "4.0\u202fGB" - ], - [ - "7b-q4_0", - "4.0\u202fGB" - ], - [ - "7b-q4_1", - "4.5\u202fGB" - ], - [ - "7b-q4_K_S", "4.1\u202fGB" ], [ - "7b-q4_K_M", + "7b", + "4.1\u202fGB" + ], + [ + "141b", + "80\u202fGB" + ], + [ + "7b-alpha", + "4.1\u202fGB" + ], + [ + "7b-beta", + "4.1\u202fGB" + ], + [ + "141b-v0.1", + "80\u202fGB" + ], + [ + "7b-alpha-fp16", + "14\u202fGB" + ], + [ + "7b-alpha-q2_K", + "3.1\u202fGB" + ], + [ + "7b-alpha-q3_K_S", + "3.2\u202fGB" + ], + [ + "7b-alpha-q3_K_M", + "3.5\u202fGB" + ], + [ + "7b-alpha-q3_K_L", + "3.8\u202fGB" + ], + [ + "7b-alpha-q4_0", + "4.1\u202fGB" + ], + [ + "7b-alpha-q4_1", + "4.6\u202fGB" + ], + [ + "7b-alpha-q4_K_S", + "4.1\u202fGB" + ], + [ + "7b-alpha-q4_K_M", "4.4\u202fGB" ], [ - "7b-q5_0", - "4.9\u202fGB" + "7b-alpha-q5_0", + "5.0\u202fGB" ], [ - "7b-q5_1", + "7b-alpha-q5_1", "5.4\u202fGB" ], [ - "7b-q5_K_S", - "4.9\u202fGB" + "7b-alpha-q5_K_S", + "5.0\u202fGB" ], [ - "7b-q5_K_M", + "7b-alpha-q5_K_M", "5.1\u202fGB" ], [ - "7b-q6_K", + "7b-alpha-q6_K", "5.9\u202fGB" ], [ - "7b-q8_0", - "7.6\u202fGB" + "7b-alpha-q8_0", + "7.7\u202fGB" ], [ - "15b-fp16", - "32\u202fGB" + "7b-beta-fp16", + "14\u202fGB" ], [ - "15b-q2_K", - "6.2\u202fGB" + "7b-beta-q2_K", + "3.1\u202fGB" ], [ - "15b-q3_K_S", - "7.0\u202fGB" + "7b-beta-q3_K_S", + "3.2\u202fGB" ], [ - "15b-q3_K_M", - "8.1\u202fGB" + "7b-beta-q3_K_M", + "3.5\u202fGB" ], [ - "15b-q3_K_L", - "9.0\u202fGB" + "7b-beta-q3_K_L", + "3.8\u202fGB" ], [ - "15b-q4_0", - "9.1\u202fGB" + "7b-beta-q4_0", + "4.1\u202fGB" ], [ - "15b-q4_1", - "10\u202fGB" + "7b-beta-q4_1", + "4.6\u202fGB" ], [ - "15b-q4_K_S", - "9.3\u202fGB" + "7b-beta-q4_K_S", + "4.1\u202fGB" ], [ - "15b-q4_K_M", - "9.9\u202fGB" + "7b-beta-q4_K_M", + "4.4\u202fGB" ], [ - "15b-q5_0", - "11\u202fGB" + "7b-beta-q5_0", + "5.0\u202fGB" ], [ - "15b-q5_1", - "12\u202fGB" + "7b-beta-q5_1", + "5.4\u202fGB" ], [ - "15b-q5_K_S", - "11\u202fGB" + "7b-beta-q5_K_S", + "5.0\u202fGB" ], [ - "15b-q5_K_M", - "11\u202fGB" + "7b-beta-q5_K_M", + "5.1\u202fGB" ], [ - "15b-q6_K", - "13\u202fGB" + "7b-beta-q6_K", + "5.9\u202fGB" ], [ - "15b-q8_0", - "17\u202fGB" + "7b-beta-q8_0", + "7.7\u202fGB" ], [ - "15b-instruct-q4_0", - "9.1\u202fGB" + "141b-v0.1-fp16", + "281\u202fGB" ], [ - "15b-instruct-v0.1-fp16", - "32\u202fGB" + "141b-v0.1-q2_K", + "52\u202fGB" ], [ - "15b-instruct-v0.1-q2_K", - "6.2\u202fGB" + "141b-v0.1-q4_0", + "80\u202fGB" ], [ - "15b-instruct-v0.1-q3_K_S", - "7.0\u202fGB" - ], - [ - "15b-instruct-v0.1-q3_K_M", - "8.0\u202fGB" - ], - [ - "15b-instruct-v0.1-q3_K_L", - "9.0\u202fGB" - ], - [ - "15b-instruct-v0.1-q4_0", - "9.1\u202fGB" - ], - [ - "15b-instruct-v0.1-q4_1", - "10\u202fGB" - ], - [ - "15b-instruct-v0.1-q4_K_S", - "9.2\u202fGB" - ], - [ - "15b-instruct-v0.1-q4_K_M", - "9.9\u202fGB" - ], - [ - "15b-instruct-v0.1-q5_0", - "11\u202fGB" - ], - [ - "15b-instruct-v0.1-q5_1", - "12\u202fGB" - ], - [ - "15b-instruct-v0.1-q5_K_S", - "11\u202fGB" - ], - [ - "15b-instruct-v0.1-q5_K_M", - "11\u202fGB" - ], - [ - "15b-instruct-v0.1-q6_K", - "13\u202fGB" - ], - [ - "15b-instruct-v0.1-q8_0", - "17\u202fGB" + "141b-v0.1-q8_0", + "149\u202fGB" ] ], "image": false, - "author": "BigCode" + "author": "Hugging Face H4" + }, + "dolphin-llama3": { + "url": "https://ollama.com/library/dolphin-llama3", + "description": "Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills.", + "tags": [ + [ + "latest", + "4.7\u202fGB" + ], + [ + "8b", + "4.7\u202fGB" + ], + [ + "70b", + "40\u202fGB" + ], + [ + "v2.9", + "4.7\u202fGB" + ], + [ + "8b-256k", + "4.7\u202fGB" + ], + [ + "8b-256k-v2.9", + "4.7\u202fGB" + ], + [ + "8b-v2.9", + "4.7\u202fGB" + ], + [ + "70b-v2.9", + "40\u202fGB" + ], + [ + "8b-256k-v2.9-fp16", + "16\u202fGB" + ], + [ + "8b-256k-v2.9-q2_K", + "3.2\u202fGB" + ], + [ + "8b-256k-v2.9-q3_K_S", + "3.7\u202fGB" + ], + [ + "8b-256k-v2.9-q3_K_M", + "4.0\u202fGB" + ], + [ + "8b-256k-v2.9-q3_K_L", + "4.3\u202fGB" + ], + [ + "8b-256k-v2.9-q4_0", + "4.7\u202fGB" + ], + [ + "8b-256k-v2.9-q4_1", + "5.1\u202fGB" + ], + [ + "8b-256k-v2.9-q4_K_S", + "4.7\u202fGB" + ], + [ + "8b-256k-v2.9-q4_K_M", + "4.9\u202fGB" + ], + [ + "8b-256k-v2.9-q5_0", + "5.6\u202fGB" + ], + [ + "8b-256k-v2.9-q5_1", + "6.1\u202fGB" + ], + [ + "8b-256k-v2.9-q5_K_S", + "5.6\u202fGB" + ], + [ + "8b-256k-v2.9-q5_K_M", + "5.7\u202fGB" + ], + [ + "8b-256k-v2.9-q6_K", + "6.6\u202fGB" + ], + [ + "8b-256k-v2.9-q8_0", + "8.5\u202fGB" + ], + [ + "8b-v2.9-fp16", + "16\u202fGB" + ], + [ + "8b-v2.9-q2_K", + "3.2\u202fGB" + ], + [ + "8b-v2.9-q3_K_S", + "3.7\u202fGB" + ], + [ + "8b-v2.9-q3_K_M", + "4.0\u202fGB" + ], + [ + "8b-v2.9-q3_K_L", + "4.3\u202fGB" + ], + [ + "8b-v2.9-q4_0", + "4.7\u202fGB" + ], + [ + "8b-v2.9-q4_1", + "5.1\u202fGB" + ], + [ + "8b-v2.9-q4_K_S", + "4.7\u202fGB" + ], + [ + "8b-v2.9-q4_K_M", + "4.9\u202fGB" + ], + [ + "8b-v2.9-q5_0", + "5.6\u202fGB" + ], + [ + "8b-v2.9-q5_1", + "6.1\u202fGB" + ], + [ + "8b-v2.9-q5_K_S", + "5.6\u202fGB" + ], + [ + "8b-v2.9-q5_K_M", + "5.7\u202fGB" + ], + [ + "8b-v2.9-q6_K", + "6.6\u202fGB" + ], + [ + "8b-v2.9-q8_0", + "8.5\u202fGB" + ], + [ + "70b-v2.9-fp16", + "141\u202fGB" + ], + [ + "70b-v2.9-q2_K", + "26\u202fGB" + ], + [ + "70b-v2.9-q3_K_S", + "31\u202fGB" + ], + [ + "70b-v2.9-q3_K_M", + "34\u202fGB" + ], + [ + "70b-v2.9-q3_K_L", + "37\u202fGB" + ], + [ + "70b-v2.9-q4_0", + "40\u202fGB" + ], + [ + "70b-v2.9-q4_1", + "44\u202fGB" + ], + [ + "70b-v2.9-q4_K_S", + "40\u202fGB" + ], + [ + "70b-v2.9-q4_K_M", + "43\u202fGB" + ], + [ + "70b-v2.9-q5_0", + "49\u202fGB" + ], + [ + "70b-v2.9-q5_1", + "53\u202fGB" + ], + [ + "70b-v2.9-q5_K_S", + "49\u202fGB" + ], + [ + "70b-v2.9-q5_K_M", + "50\u202fGB" + ], + [ + "70b-v2.9-q6_K", + "58\u202fGB" + ], + [ + "70b-v2.9-q8_0", + "75\u202fGB" + ] + ], + "image": false, + "author": "Eric Hartford" }, "orca-mini": { "url": "https://ollama.com/library/orca-mini", @@ -9323,230 +10291,6 @@ "image": false, "author": "Orca Mini Team" }, - "dolphin-llama3": { - "url": "https://ollama.com/library/dolphin-llama3", - "description": "Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills.", - "tags": [ - [ - "latest", - "4.7\u202fGB" - ], - [ - "256k", - "4.7\u202fGB" - ], - [ - "8b", - "4.7\u202fGB" - ], - [ - "70b", - "40\u202fGB" - ], - [ - "v2.9", - "4.7\u202fGB" - ], - [ - "8b-256k", - "4.7\u202fGB" - ], - [ - "8b-256k-v2.9", - "4.7\u202fGB" - ], - [ - "8b-v2.9", - "4.7\u202fGB" - ], - [ - "70b-v2.9", - "40\u202fGB" - ], - [ - "8b-256k-v2.9-fp16", - "16\u202fGB" - ], - [ - "8b-256k-v2.9-q2_K", - "3.2\u202fGB" - ], - [ - "8b-256k-v2.9-q3_K_S", - "3.7\u202fGB" - ], - [ - "8b-256k-v2.9-q3_K_M", - "4.0\u202fGB" - ], - [ - "8b-256k-v2.9-q3_K_L", - "4.3\u202fGB" - ], - [ - "8b-256k-v2.9-q4_0", - "4.7\u202fGB" - ], - [ - "8b-256k-v2.9-q4_1", - "5.1\u202fGB" - ], - [ - "8b-256k-v2.9-q4_K_S", - "4.7\u202fGB" - ], - [ - "8b-256k-v2.9-q4_K_M", - "4.9\u202fGB" - ], - [ - "8b-256k-v2.9-q5_0", - "5.6\u202fGB" - ], - [ - "8b-256k-v2.9-q5_1", - "6.1\u202fGB" - ], - [ - "8b-256k-v2.9-q5_K_S", - "5.6\u202fGB" - ], - [ - "8b-256k-v2.9-q5_K_M", - "5.7\u202fGB" - ], - [ - "8b-256k-v2.9-q6_K", - "6.6\u202fGB" - ], - [ - "8b-256k-v2.9-q8_0", - "8.5\u202fGB" - ], - [ - "8b-v2.9-fp16", - "16\u202fGB" - ], - [ - "8b-v2.9-q2_K", - "3.2\u202fGB" - ], - [ - "8b-v2.9-q3_K_S", - "3.7\u202fGB" - ], - [ - "8b-v2.9-q3_K_M", - "4.0\u202fGB" - ], - [ - "8b-v2.9-q3_K_L", - "4.3\u202fGB" - ], - [ - "8b-v2.9-q4_0", - "4.7\u202fGB" - ], - [ - "8b-v2.9-q4_1", - "5.1\u202fGB" - ], - [ - "8b-v2.9-q4_K_S", - "4.7\u202fGB" - ], - [ - "8b-v2.9-q4_K_M", - "4.9\u202fGB" - ], - [ - "8b-v2.9-q5_0", - "5.6\u202fGB" - ], - [ - "8b-v2.9-q5_1", - "6.1\u202fGB" - ], - [ - "8b-v2.9-q5_K_S", - "5.6\u202fGB" - ], - [ - "8b-v2.9-q5_K_M", - "5.7\u202fGB" - ], - [ - "8b-v2.9-q6_K", - "6.6\u202fGB" - ], - [ - "8b-v2.9-q8_0", - "8.5\u202fGB" - ], - [ - "70b-v2.9-fp16", - "141\u202fGB" - ], - [ - "70b-v2.9-q2_K", - "26\u202fGB" - ], - [ - "70b-v2.9-q3_K_S", - "31\u202fGB" - ], - [ - "70b-v2.9-q3_K_M", - "34\u202fGB" - ], - [ - "70b-v2.9-q3_K_L", - "37\u202fGB" - ], - [ - "70b-v2.9-q4_0", - "40\u202fGB" - ], - [ - "70b-v2.9-q4_1", - "44\u202fGB" - ], - [ - "70b-v2.9-q4_K_S", - "40\u202fGB" - ], - [ - "70b-v2.9-q4_K_M", - "43\u202fGB" - ], - [ - "70b-v2.9-q5_0", - "49\u202fGB" - ], - [ - "70b-v2.9-q5_1", - "53\u202fGB" - ], - [ - "70b-v2.9-q5_K_S", - "49\u202fGB" - ], - [ - "70b-v2.9-q5_K_M", - "50\u202fGB" - ], - [ - "70b-v2.9-q6_K", - "58\u202fGB" - ], - [ - "70b-v2.9-q8_0", - "75\u202fGB" - ] - ], - "image": false, - "author": "Eric Hartford" - }, "yi": { "url": "https://ollama.com/library/yi", "description": "Yi 1.5 is a high-performing, bilingual language model.", @@ -10251,6 +10995,30 @@ "image": false, "author": "01.AI" }, + "llava-llama3": { + "url": "https://ollama.com/library/llava-llama3", + "description": "A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.", + "tags": [ + [ + "latest", + "5.5\u202fGB" + ], + [ + "8b", + "5.5\u202fGB" + ], + [ + "8b-v1.1-fp16", + "17\u202fGB" + ], + [ + "8b-v1.1-q4_0", + "5.5\u202fGB" + ] + ], + "image": true, + "author": "Xtuner" + }, "mistral-openorca": { "url": "https://ollama.com/library/mistral-openorca", "description": "Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.", @@ -10327,30 +11095,6 @@ "image": false, "author": "Open Orca" }, - "llava-llama3": { - "url": "https://ollama.com/library/llava-llama3", - "description": "A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.", - "tags": [ - [ - "latest", - "5.5\u202fGB" - ], - [ - "8b", - "5.5\u202fGB" - ], - [ - "8b-v1.1-fp16", - "17\u202fGB" - ], - [ - "8b-v1.1-q4_0", - "5.5\u202fGB" - ] - ], - "image": true, - "author": "Xtuner" - }, "starcoder": { "url": "https://ollama.com/library/starcoder", "description": "StarCoder is a code generation model trained on 80+ programming languages.", @@ -10759,153 +11503,157 @@ "image": false, "author": "BigCode" }, - "llama2-chinese": { - "url": "https://ollama.com/library/llama2-chinese", - "description": "Llama 2 based model fine tuned to improve Chinese dialogue ability.", + "tinyllama": { + "url": "https://ollama.com/library/tinyllama", + "description": "The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.", "tags": [ [ "latest", - "3.8\u202fGB" + "638\u202fMB" ], [ - "7b", - "3.8\u202fGB" + "1.1b", + "638\u202fMB" ], [ - "13b", - "7.4\u202fGB" + "chat", + "638\u202fMB" ], [ - "7b-chat", - "3.8\u202fGB" + "v0.6", + "638\u202fMB" ], [ - "13b-chat", - "7.4\u202fGB" + "v1", + "638\u202fMB" ], [ - "7b-chat-fp16", - "13\u202fGB" + "1.1b-chat", + "638\u202fMB" ], [ - "7b-chat-q2_K", - "2.8\u202fGB" + "1.1b-chat-v0.6-fp16", + "2.2\u202fGB" ], [ - "7b-chat-q3_K_S", - "2.9\u202fGB" + "1.1b-chat-v0.6-q2_K", + "483\u202fMB" ], [ - "7b-chat-q3_K_M", - "3.3\u202fGB" + "1.1b-chat-v0.6-q3_K_S", + "500\u202fMB" ], [ - "7b-chat-q3_K_L", - "3.6\u202fGB" + "1.1b-chat-v0.6-q3_K_M", + "551\u202fMB" ], [ - "7b-chat-q4_0", - "3.8\u202fGB" + "1.1b-chat-v0.6-q3_K_L", + "593\u202fMB" ], [ - "7b-chat-q4_1", - "4.2\u202fGB" + "1.1b-chat-v0.6-q4_0", + "638\u202fMB" ], [ - "7b-chat-q4_K_S", - "3.9\u202fGB" + "1.1b-chat-v0.6-q4_1", + "702\u202fMB" ], [ - "7b-chat-q4_K_M", - "4.1\u202fGB" + "1.1b-chat-v0.6-q4_K_S", + "644\u202fMB" ], [ - "7b-chat-q5_0", - "4.7\u202fGB" + "1.1b-chat-v0.6-q4_K_M", + "669\u202fMB" ], [ - "7b-chat-q5_1", - "5.1\u202fGB" + "1.1b-chat-v0.6-q5_0", + "767\u202fMB" ], [ - "7b-chat-q5_K_S", - "4.7\u202fGB" + "1.1b-chat-v0.6-q5_1", + "832\u202fMB" ], [ - "7b-chat-q5_K_M", - "4.8\u202fGB" + "1.1b-chat-v0.6-q5_K_S", + "767\u202fMB" ], [ - "7b-chat-q6_K", - "5.5\u202fGB" + "1.1b-chat-v0.6-q5_K_M", + "783\u202fMB" ], [ - "7b-chat-q8_0", - "7.2\u202fGB" + "1.1b-chat-v0.6-q6_K", + "904\u202fMB" ], [ - "13b-chat-fp16", - "26\u202fGB" + "1.1b-chat-v0.6-q8_0", + "1.2\u202fGB" ], [ - "13b-chat-q2_K", - "5.4\u202fGB" + "1.1b-chat-v1-fp16", + "2.2\u202fGB" ], [ - "13b-chat-q3_K_S", - "5.7\u202fGB" + "1.1b-chat-v1-q2_K", + "483\u202fMB" ], [ - "13b-chat-q3_K_M", - "6.3\u202fGB" + "1.1b-chat-v1-q3_K_S", + "500\u202fMB" ], [ - "13b-chat-q3_K_L", - "6.9\u202fGB" + "1.1b-chat-v1-q3_K_M", + "551\u202fMB" ], [ - "13b-chat-q4_0", - "7.4\u202fGB" + "1.1b-chat-v1-q3_K_L", + "593\u202fMB" ], [ - "13b-chat-q4_1", - "8.2\u202fGB" + "1.1b-chat-v1-q4_0", + "638\u202fMB" ], [ - "13b-chat-q4_K_S", - "7.4\u202fGB" + "1.1b-chat-v1-q4_1", + "702\u202fMB" ], [ - "13b-chat-q4_K_M", - "7.9\u202fGB" + "1.1b-chat-v1-q4_K_S", + "644\u202fMB" ], [ - "13b-chat-q5_0", - "9.0\u202fGB" + "1.1b-chat-v1-q4_K_M", + "669\u202fMB" ], [ - "13b-chat-q5_1", - "9.8\u202fGB" + "1.1b-chat-v1-q5_0", + "767\u202fMB" ], [ - "13b-chat-q5_K_S", - "9.0\u202fGB" + "1.1b-chat-v1-q5_1", + "832\u202fMB" ], [ - "13b-chat-q5_K_M", - "9.2\u202fGB" + "1.1b-chat-v1-q5_K_S", + "767\u202fMB" ], [ - "13b-chat-q6_K", - "11\u202fGB" + "1.1b-chat-v1-q5_K_M", + "783\u202fMB" ], [ - "13b-chat-q8_0", - "14\u202fGB" + "1.1b-chat-v1-q6_K", + "904\u202fMB" + ], + [ + "1.1b-chat-v1-q8_0", + "1.2\u202fGB" ] ], "image": false, - "author": "Meta" + "author": "TinyLlama Team" }, "vicuna": { "url": "https://ollama.com/library/vicuna", @@ -11359,158 +12107,6 @@ "image": false, "author": "lmsys.org" }, - "tinyllama": { - "url": "https://ollama.com/library/tinyllama", - "description": "The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.", - "tags": [ - [ - "latest", - "638\u202fMB" - ], - [ - "1.1b", - "638\u202fMB" - ], - [ - "chat", - "638\u202fMB" - ], - [ - "v0.6", - "638\u202fMB" - ], - [ - "v1", - "638\u202fMB" - ], - [ - "1.1b-chat", - "638\u202fMB" - ], - [ - "1.1b-chat-v0.6-fp16", - "2.2\u202fGB" - ], - [ - "1.1b-chat-v0.6-q2_K", - "483\u202fMB" - ], - [ - "1.1b-chat-v0.6-q3_K_S", - "500\u202fMB" - ], - [ - "1.1b-chat-v0.6-q3_K_M", - "551\u202fMB" - ], - [ - "1.1b-chat-v0.6-q3_K_L", - "593\u202fMB" - ], - [ - "1.1b-chat-v0.6-q4_0", - "638\u202fMB" - ], - [ - "1.1b-chat-v0.6-q4_1", - "702\u202fMB" - ], - [ - "1.1b-chat-v0.6-q4_K_S", - "644\u202fMB" - ], - [ - "1.1b-chat-v0.6-q4_K_M", - "669\u202fMB" - ], - [ - "1.1b-chat-v0.6-q5_0", - "767\u202fMB" - ], - [ - "1.1b-chat-v0.6-q5_1", - "832\u202fMB" - ], - [ - "1.1b-chat-v0.6-q5_K_S", - "767\u202fMB" - ], - [ - "1.1b-chat-v0.6-q5_K_M", - "783\u202fMB" - ], - [ - "1.1b-chat-v0.6-q6_K", - "904\u202fMB" - ], - [ - "1.1b-chat-v0.6-q8_0", - "1.2\u202fGB" - ], - [ - "1.1b-chat-v1-fp16", - "2.2\u202fGB" - ], - [ - "1.1b-chat-v1-q2_K", - "483\u202fMB" - ], - [ - "1.1b-chat-v1-q3_K_S", - "500\u202fMB" - ], - [ - "1.1b-chat-v1-q3_K_M", - "551\u202fMB" - ], - [ - "1.1b-chat-v1-q3_K_L", - "593\u202fMB" - ], - [ - "1.1b-chat-v1-q4_0", - "638\u202fMB" - ], - [ - "1.1b-chat-v1-q4_1", - "702\u202fMB" - ], - [ - "1.1b-chat-v1-q4_K_S", - "644\u202fMB" - ], - [ - "1.1b-chat-v1-q4_K_M", - "669\u202fMB" - ], - [ - "1.1b-chat-v1-q5_0", - "767\u202fMB" - ], - [ - "1.1b-chat-v1-q5_1", - "832\u202fMB" - ], - [ - "1.1b-chat-v1-q5_K_S", - "767\u202fMB" - ], - [ - "1.1b-chat-v1-q5_K_M", - "783\u202fMB" - ], - [ - "1.1b-chat-v1-q6_K", - "904\u202fMB" - ], - [ - "1.1b-chat-v1-q8_0", - "1.2\u202fGB" - ] - ], - "image": false, - "author": "TinyLlama Team" - }, "codestral": { "url": "https://ollama.com/library/codestral", "description": "Codestral is Mistral AI\u2019s first-ever code model designed for code generation tasks.", @@ -11527,10 +12123,6 @@ "v0.1", "13\u202fGB" ], - [ - "22b-v0.1-f16", - "44\u202fGB" - ], [ "22b-v0.1-q2_K", "8.3\u202fGB" @@ -11591,6 +12183,154 @@ "image": false, "author": "Mistral AI" }, + "llama2-chinese": { + "url": "https://ollama.com/library/llama2-chinese", + "description": "Llama 2 based model fine tuned to improve Chinese dialogue ability.", + "tags": [ + [ + "latest", + "3.8\u202fGB" + ], + [ + "7b", + "3.8\u202fGB" + ], + [ + "13b", + "7.4\u202fGB" + ], + [ + "7b-chat", + "3.8\u202fGB" + ], + [ + "13b-chat", + "7.4\u202fGB" + ], + [ + "7b-chat-fp16", + "13\u202fGB" + ], + [ + "7b-chat-q2_K", + "2.8\u202fGB" + ], + [ + "7b-chat-q3_K_S", + "2.9\u202fGB" + ], + [ + "7b-chat-q3_K_M", + "3.3\u202fGB" + ], + [ + "7b-chat-q3_K_L", + "3.6\u202fGB" + ], + [ + "7b-chat-q4_0", + "3.8\u202fGB" + ], + [ + "7b-chat-q4_1", + "4.2\u202fGB" + ], + [ + "7b-chat-q4_K_S", + "3.9\u202fGB" + ], + [ + "7b-chat-q4_K_M", + "4.1\u202fGB" + ], + [ + "7b-chat-q5_0", + "4.7\u202fGB" + ], + [ + "7b-chat-q5_1", + "5.1\u202fGB" + ], + [ + "7b-chat-q5_K_S", + "4.7\u202fGB" + ], + [ + "7b-chat-q5_K_M", + "4.8\u202fGB" + ], + [ + "7b-chat-q6_K", + "5.5\u202fGB" + ], + [ + "7b-chat-q8_0", + "7.2\u202fGB" + ], + [ + "13b-chat-fp16", + "26\u202fGB" + ], + [ + "13b-chat-q2_K", + "5.4\u202fGB" + ], + [ + "13b-chat-q3_K_S", + "5.7\u202fGB" + ], + [ + "13b-chat-q3_K_M", + "6.3\u202fGB" + ], + [ + "13b-chat-q3_K_L", + "6.9\u202fGB" + ], + [ + "13b-chat-q4_0", + "7.4\u202fGB" + ], + [ + "13b-chat-q4_1", + "8.2\u202fGB" + ], + [ + "13b-chat-q4_K_S", + "7.4\u202fGB" + ], + [ + "13b-chat-q4_K_M", + "7.9\u202fGB" + ], + [ + "13b-chat-q5_0", + "9.0\u202fGB" + ], + [ + "13b-chat-q5_1", + "9.8\u202fGB" + ], + [ + "13b-chat-q5_K_S", + "9.0\u202fGB" + ], + [ + "13b-chat-q5_K_M", + "9.2\u202fGB" + ], + [ + "13b-chat-q6_K", + "11\u202fGB" + ], + [ + "13b-chat-q8_0", + "14\u202fGB" + ] + ], + "image": false, + "author": "Meta" + }, "wizard-vicuna-uncensored": { "url": "https://ollama.com/library/wizard-vicuna-uncensored", "description": "Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.", @@ -11795,6 +12535,82 @@ "image": false, "author": "Eric Hartford" }, + "codegeex4": { + "url": "https://ollama.com/library/codegeex4", + "description": "A versatile model for AI software development scenarios, including code completion.", + "tags": [ + [ + "latest", + "5.5\u202fGB" + ], + [ + "9b", + "5.5\u202fGB" + ], + [ + "9b-all-fp16", + "19\u202fGB" + ], + [ + "9b-all-q2_K", + "4.0\u202fGB" + ], + [ + "9b-all-q3_K_S", + "4.6\u202fGB" + ], + [ + "9b-all-q3_K_M", + "5.1\u202fGB" + ], + [ + "9b-all-q3_K_L", + "5.3\u202fGB" + ], + [ + "9b-all-q4_0", + "5.5\u202fGB" + ], + [ + "9b-all-q4_1", + "6.0\u202fGB" + ], + [ + "9b-all-q4_K_S", + "5.8\u202fGB" + ], + [ + "9b-all-q4_K_M", + "6.3\u202fGB" + ], + [ + "9b-all-q5_0", + "6.6\u202fGB" + ], + [ + "9b-all-q5_1", + "7.1\u202fGB" + ], + [ + "9b-all-q5_K_S", + "6.7\u202fGB" + ], + [ + "9b-all-q5_K_M", + "7.1\u202fGB" + ], + [ + "9b-all-q6_K", + "8.3\u202fGB" + ], + [ + "9b-all-q8_0", + "10.0\u202fGB" + ] + ], + "image": false, + "author": "THUDM" + }, "nous-hermes2": { "url": "https://ollama.com/library/nous-hermes2", "description": "The powerful family of models by Nous Research that excels at scientific discussion and coding tasks.", @@ -11935,538 +12751,6 @@ "image": false, "author": "Nous Research" }, - "openchat": { - "url": "https://ollama.com/library/openchat", - "description": "A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106.", - "tags": [ - [ - "latest", - "4.1\u202fGB" - ], - [ - "7b", - "4.1\u202fGB" - ], - [ - "7b-v3.5", - "4.1\u202fGB" - ], - [ - "7b-v3.5-0106", - "4.1\u202fGB" - ], - [ - "7b-v3.5-1210", - "4.1\u202fGB" - ], - [ - "7b-v3.5-fp16", - "14\u202fGB" - ], - [ - "7b-v3.5-q2_K", - "3.1\u202fGB" - ], - [ - "7b-v3.5-q3_K_S", - "3.2\u202fGB" - ], - [ - "7b-v3.5-q3_K_M", - "3.5\u202fGB" - ], - [ - "7b-v3.5-q3_K_L", - "3.8\u202fGB" - ], - [ - "7b-v3.5-q4_0", - "4.1\u202fGB" - ], - [ - "7b-v3.5-q4_1", - "4.6\u202fGB" - ], - [ - "7b-v3.5-q4_K_S", - "4.1\u202fGB" - ], - [ - "7b-v3.5-q4_K_M", - "4.4\u202fGB" - ], - [ - "7b-v3.5-q5_0", - "5.0\u202fGB" - ], - [ - "7b-v3.5-q5_1", - "5.4\u202fGB" - ], - [ - "7b-v3.5-q5_K_S", - "5.0\u202fGB" - ], - [ - "7b-v3.5-q5_K_M", - "5.1\u202fGB" - ], - [ - "7b-v3.5-q6_K", - "5.9\u202fGB" - ], - [ - "7b-v3.5-q8_0", - "7.7\u202fGB" - ], - [ - "7b-v3.5-0106-fp16", - "14\u202fGB" - ], - [ - "7b-v3.5-0106-q2_K", - "3.1\u202fGB" - ], - [ - "7b-v3.5-0106-q3_K_S", - "3.2\u202fGB" - ], - [ - "7b-v3.5-0106-q3_K_M", - "3.5\u202fGB" - ], - [ - "7b-v3.5-0106-q3_K_L", - "3.8\u202fGB" - ], - [ - "7b-v3.5-0106-q4_0", - "4.1\u202fGB" - ], - [ - "7b-v3.5-0106-q4_1", - "4.6\u202fGB" - ], - [ - "7b-v3.5-0106-q4_K_S", - "4.1\u202fGB" - ], - [ - "7b-v3.5-0106-q4_K_M", - "4.4\u202fGB" - ], - [ - "7b-v3.5-0106-q5_0", - "5.0\u202fGB" - ], - [ - "7b-v3.5-0106-q5_1", - "5.4\u202fGB" - ], - [ - "7b-v3.5-0106-q5_K_S", - "5.0\u202fGB" - ], - [ - "7b-v3.5-0106-q5_K_M", - "5.1\u202fGB" - ], - [ - "7b-v3.5-0106-q6_K", - "5.9\u202fGB" - ], - [ - "7b-v3.5-0106-q8_0", - "7.7\u202fGB" - ], - [ - "7b-v3.5-1210-fp16", - "14\u202fGB" - ], - [ - "7b-v3.5-1210-q2_K", - "3.1\u202fGB" - ], - [ - "7b-v3.5-1210-q3_K_S", - "3.2\u202fGB" - ], - [ - "7b-v3.5-1210-q3_K_M", - "3.5\u202fGB" - ], - [ - "7b-v3.5-1210-q3_K_L", - "3.8\u202fGB" - ], - [ - "7b-v3.5-1210-q4_0", - "4.1\u202fGB" - ], - [ - "7b-v3.5-1210-q4_1", - "4.6\u202fGB" - ], - [ - "7b-v3.5-1210-q4_K_S", - "4.1\u202fGB" - ], - [ - "7b-v3.5-1210-q4_K_M", - "4.4\u202fGB" - ], - [ - "7b-v3.5-1210-q5_0", - "5.0\u202fGB" - ], - [ - "7b-v3.5-1210-q5_1", - "5.4\u202fGB" - ], - [ - "7b-v3.5-1210-q5_K_S", - "5.0\u202fGB" - ], - [ - "7b-v3.5-1210-q5_K_M", - "5.1\u202fGB" - ], - [ - "7b-v3.5-1210-q6_K", - "5.9\u202fGB" - ], - [ - "7b-v3.5-1210-q8_0", - "7.7\u202fGB" - ] - ], - "image": false, - "author": "OpenChat Team" - }, - "aya": { - "url": "https://ollama.com/library/aya", - "description": "Aya 23, released by Cohere, is a new family of state-of-the-art, multilingual models that support 23 languages.", - "tags": [ - [ - "latest", - "4.8\u202fGB" - ], - [ - "8b", - "4.8\u202fGB" - ], - [ - "35b", - "20\u202fGB" - ], - [ - "8b-23", - "4.8\u202fGB" - ], - [ - "8b-23-f16", - "16\u202fGB" - ], - [ - "35b-23", - "20\u202fGB" - ], - [ - "35b-23-f16", - "70\u202fGB" - ], - [ - "8b-23-q2_K", - "3.4\u202fGB" - ], - [ - "8b-23-q3_K_S", - "3.9\u202fGB" - ], - [ - "8b-23-q3_K_M", - "4.2\u202fGB" - ], - [ - "8b-23-q3_K_L", - "4.5\u202fGB" - ], - [ - "8b-23-q4_0", - "4.8\u202fGB" - ], - [ - "8b-23-q4_1", - "5.2\u202fGB" - ], - [ - "8b-23-q4_K_S", - "4.8\u202fGB" - ], - [ - "8b-23-q4_K_M", - "5.1\u202fGB" - ], - [ - "8b-23-q5_0", - "5.7\u202fGB" - ], - [ - "8b-23-q5_1", - "6.1\u202fGB" - ], - [ - "8b-23-q5_K_S", - "5.7\u202fGB" - ], - [ - "8b-23-q5_K_M", - "5.8\u202fGB" - ], - [ - "8b-23-q6_K", - "6.6\u202fGB" - ], - [ - "8b-23-q8_0", - "8.5\u202fGB" - ], - [ - "35b-23-q2_K", - "14\u202fGB" - ], - [ - "35b-23-q3_K_S", - "16\u202fGB" - ], - [ - "35b-23-q3_K_M", - "18\u202fGB" - ], - [ - "35b-23-q3_K_L", - "19\u202fGB" - ], - [ - "35b-23-q4_0", - "20\u202fGB" - ], - [ - "35b-23-q4_1", - "22\u202fGB" - ], - [ - "35b-23-q4_K_S", - "20\u202fGB" - ], - [ - "35b-23-q4_K_M", - "22\u202fGB" - ], - [ - "35b-23-q5_0", - "24\u202fGB" - ], - [ - "35b-23-q5_1", - "26\u202fGB" - ], - [ - "35b-23-q5_K_S", - "24\u202fGB" - ], - [ - "35b-23-q5_K_M", - "25\u202fGB" - ], - [ - "35b-23-q6_K", - "29\u202fGB" - ], - [ - "35b-23-q8_0", - "37\u202fGB" - ] - ], - "image": false, - "author": "Cohere" - }, - "wizardlm2": { - "url": "https://ollama.com/library/wizardlm2", - "description": "State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.", - "tags": [ - [ - "latest", - "4.1\u202fGB" - ], - [ - "7b", - "4.1\u202fGB" - ], - [ - "8x22b", - "80\u202fGB" - ], - [ - "7b-fp16", - "14\u202fGB" - ], - [ - "7b-q2_K", - "2.7\u202fGB" - ], - [ - "7b-q3_K_S", - "3.2\u202fGB" - ], - [ - "7b-q3_K_M", - "3.5\u202fGB" - ], - [ - "7b-q3_K_L", - "3.8\u202fGB" - ], - [ - "7b-q4_0", - "4.1\u202fGB" - ], - [ - "7b-q4_1", - "4.6\u202fGB" - ], - [ - "7b-q4_K_S", - "4.1\u202fGB" - ], - [ - "7b-q4_K_M", - "4.4\u202fGB" - ], - [ - "7b-q5_0", - "5.0\u202fGB" - ], - [ - "7b-q5_1", - "5.4\u202fGB" - ], - [ - "7b-q5_K_S", - "5.0\u202fGB" - ], - [ - "7b-q5_K_M", - "5.1\u202fGB" - ], - [ - "7b-q6_K", - "5.9\u202fGB" - ], - [ - "7b-q8_0", - "7.7\u202fGB" - ], - [ - "8x22b-fp16", - "281\u202fGB" - ], - [ - "8x22b-q2_K", - "52\u202fGB" - ], - [ - "8x22b-q4_0", - "80\u202fGB" - ], - [ - "8x22b-q8_0", - "149\u202fGB" - ] - ], - "image": false, - "author": "Microsoft" - }, - "tinydolphin": { - "url": "https://ollama.com/library/tinydolphin", - "description": "An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.", - "tags": [ - [ - "latest", - "637\u202fMB" - ], - [ - "1.1b", - "637\u202fMB" - ], - [ - "v2.8", - "637\u202fMB" - ], - [ - "1.1b-v2.8-fp16", - "2.2\u202fGB" - ], - [ - "1.1b-v2.8-q2_K", - "432\u202fMB" - ], - [ - "1.1b-v2.8-q3_K_S", - "499\u202fMB" - ], - [ - "1.1b-v2.8-q3_K_M", - "548\u202fMB" - ], - [ - "1.1b-v2.8-q3_K_L", - "592\u202fMB" - ], - [ - "1.1b-v2.8-q4_0", - "637\u202fMB" - ], - [ - "1.1b-v2.8-q4_1", - "701\u202fMB" - ], - [ - "1.1b-v2.8-q4_K_S", - "640\u202fMB" - ], - [ - "1.1b-v2.8-q4_K_M", - "668\u202fMB" - ], - [ - "1.1b-v2.8-q5_0", - "766\u202fMB" - ], - [ - "1.1b-v2.8-q5_1", - "831\u202fMB" - ], - [ - "1.1b-v2.8-q5_K_S", - "766\u202fMB" - ], - [ - "1.1b-v2.8-q5_K_M", - "782\u202fMB" - ], - [ - "1.1b-v2.8-q6_K", - "903\u202fMB" - ], - [ - "1.1b-v2.8-q8_0", - "1.2\u202fGB" - ] - ], - "image": false, - "author": "Eric Hartford" - }, "granite-code": { "url": "https://ollama.com/library/granite-code", "description": "A family of open foundation models by IBM for Code Intelligence", @@ -12495,66 +12779,34 @@ "3b-base", "2.0\u202fGB" ], - [ - "3b-base-f16", - "7.0\u202fGB" - ], [ "3b-instruct", "2.0\u202fGB" ], - [ - "3b-instruct-f16", - "7.0\u202fGB" - ], [ "8b-base", "4.6\u202fGB" ], - [ - "8b-base-f16", - "16\u202fGB" - ], [ "8b-instruct", "4.6\u202fGB" ], - [ - "8b-instruct-f16", - "16\u202fGB" - ], [ "20b-base", "12\u202fGB" ], - [ - "20b-base-f16", - "40\u202fGB" - ], [ "20b-instruct", "12\u202fGB" ], - [ - "20b-instruct-f16", - "40\u202fGB" - ], [ "34b-base", "19\u202fGB" ], - [ - "34b-base-f16", - "68\u202fGB" - ], [ "34b-instruct", "19\u202fGB" ], - [ - "34b-instruct-f16", - "68\u202fGB" - ], [ "3b-base-fp16", "7.0\u202fGB" @@ -12979,6 +13231,66 @@ "20b-instruct-q8_0", "21\u202fGB" ], + [ + "20b-instruct-8k-fp16", + "40\u202fGB" + ], + [ + "20b-instruct-8k-q2_K", + "7.9\u202fGB" + ], + [ + "20b-instruct-8k-q3_K_S", + "8.9\u202fGB" + ], + [ + "20b-instruct-8k-q3_K_M", + "11\u202fGB" + ], + [ + "20b-instruct-8k-q3_K_L", + "12\u202fGB" + ], + [ + "20b-instruct-8k-q4_0", + "12\u202fGB" + ], + [ + "20b-instruct-8k-q4_1", + "13\u202fGB" + ], + [ + "20b-instruct-8k-q4_K_S", + "12\u202fGB" + ], + [ + "20b-instruct-8k-q4_K_M", + "13\u202fGB" + ], + [ + "20b-instruct-8k-q5_0", + "14\u202fGB" + ], + [ + "20b-instruct-8k-q5_1", + "15\u202fGB" + ], + [ + "20b-instruct-8k-q5_K_S", + "14\u202fGB" + ], + [ + "20b-instruct-8k-q5_K_M", + "15\u202fGB" + ], + [ + "20b-instruct-8k-q6_K", + "17\u202fGB" + ], + [ + "20b-instruct-8k-q8_0", + "21\u202fGB" + ], [ "34b-base-q2_K", "13\u202fGB" @@ -13095,6 +13407,706 @@ "image": false, "author": "IBM for Code Intelligence" }, + "openchat": { + "url": "https://ollama.com/library/openchat", + "description": "A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106.", + "tags": [ + [ + "latest", + "4.1\u202fGB" + ], + [ + "7b", + "4.1\u202fGB" + ], + [ + "7b-v3.5", + "4.1\u202fGB" + ], + [ + "7b-v3.5-0106", + "4.1\u202fGB" + ], + [ + "7b-v3.5-1210", + "4.1\u202fGB" + ], + [ + "7b-v3.5-fp16", + "14\u202fGB" + ], + [ + "7b-v3.5-q2_K", + "3.1\u202fGB" + ], + [ + "7b-v3.5-q3_K_S", + "3.2\u202fGB" + ], + [ + "7b-v3.5-q3_K_M", + "3.5\u202fGB" + ], + [ + "7b-v3.5-q3_K_L", + "3.8\u202fGB" + ], + [ + "7b-v3.5-q4_0", + "4.1\u202fGB" + ], + [ + "7b-v3.5-q4_1", + "4.6\u202fGB" + ], + [ + "7b-v3.5-q4_K_S", + "4.1\u202fGB" + ], + [ + "7b-v3.5-q4_K_M", + "4.4\u202fGB" + ], + [ + "7b-v3.5-q5_0", + "5.0\u202fGB" + ], + [ + "7b-v3.5-q5_1", + "5.4\u202fGB" + ], + [ + "7b-v3.5-q5_K_S", + "5.0\u202fGB" + ], + [ + "7b-v3.5-q5_K_M", + "5.1\u202fGB" + ], + [ + "7b-v3.5-q6_K", + "5.9\u202fGB" + ], + [ + "7b-v3.5-q8_0", + "7.7\u202fGB" + ], + [ + "7b-v3.5-0106-fp16", + "14\u202fGB" + ], + [ + "7b-v3.5-0106-q2_K", + "3.1\u202fGB" + ], + [ + "7b-v3.5-0106-q3_K_S", + "3.2\u202fGB" + ], + [ + "7b-v3.5-0106-q3_K_M", + "3.5\u202fGB" + ], + [ + "7b-v3.5-0106-q3_K_L", + "3.8\u202fGB" + ], + [ + "7b-v3.5-0106-q4_0", + "4.1\u202fGB" + ], + [ + "7b-v3.5-0106-q4_1", + "4.6\u202fGB" + ], + [ + "7b-v3.5-0106-q4_K_S", + "4.1\u202fGB" + ], + [ + "7b-v3.5-0106-q4_K_M", + "4.4\u202fGB" + ], + [ + "7b-v3.5-0106-q5_0", + "5.0\u202fGB" + ], + [ + "7b-v3.5-0106-q5_1", + "5.4\u202fGB" + ], + [ + "7b-v3.5-0106-q5_K_S", + "5.0\u202fGB" + ], + [ + "7b-v3.5-0106-q5_K_M", + "5.1\u202fGB" + ], + [ + "7b-v3.5-0106-q6_K", + "5.9\u202fGB" + ], + [ + "7b-v3.5-0106-q8_0", + "7.7\u202fGB" + ], + [ + "7b-v3.5-1210-fp16", + "14\u202fGB" + ], + [ + "7b-v3.5-1210-q2_K", + "3.1\u202fGB" + ], + [ + "7b-v3.5-1210-q3_K_S", + "3.2\u202fGB" + ], + [ + "7b-v3.5-1210-q3_K_M", + "3.5\u202fGB" + ], + [ + "7b-v3.5-1210-q3_K_L", + "3.8\u202fGB" + ], + [ + "7b-v3.5-1210-q4_0", + "4.1\u202fGB" + ], + [ + "7b-v3.5-1210-q4_1", + "4.6\u202fGB" + ], + [ + "7b-v3.5-1210-q4_K_S", + "4.1\u202fGB" + ], + [ + "7b-v3.5-1210-q4_K_M", + "4.4\u202fGB" + ], + [ + "7b-v3.5-1210-q5_0", + "5.0\u202fGB" + ], + [ + "7b-v3.5-1210-q5_1", + "5.4\u202fGB" + ], + [ + "7b-v3.5-1210-q5_K_S", + "5.0\u202fGB" + ], + [ + "7b-v3.5-1210-q5_K_M", + "5.1\u202fGB" + ], + [ + "7b-v3.5-1210-q6_K", + "5.9\u202fGB" + ], + [ + "7b-v3.5-1210-q8_0", + "7.7\u202fGB" + ] + ], + "image": false, + "author": "OpenChat Team" + }, + "aya": { + "url": "https://ollama.com/library/aya", + "description": "Aya 23, released by Cohere, is a new family of state-of-the-art, multilingual models that support 23 languages.", + "tags": [ + [ + "latest", + "4.8\u202fGB" + ], + [ + "8b", + "4.8\u202fGB" + ], + [ + "35b", + "20\u202fGB" + ], + [ + "8b-23", + "4.8\u202fGB" + ], + [ + "35b-23", + "20\u202fGB" + ], + [ + "8b-23-q2_K", + "3.4\u202fGB" + ], + [ + "8b-23-q3_K_S", + "3.9\u202fGB" + ], + [ + "8b-23-q3_K_M", + "4.2\u202fGB" + ], + [ + "8b-23-q3_K_L", + "4.5\u202fGB" + ], + [ + "8b-23-q4_0", + "4.8\u202fGB" + ], + [ + "8b-23-q4_1", + "5.2\u202fGB" + ], + [ + "8b-23-q4_K_S", + "4.8\u202fGB" + ], + [ + "8b-23-q4_K_M", + "5.1\u202fGB" + ], + [ + "8b-23-q5_0", + "5.7\u202fGB" + ], + [ + "8b-23-q5_1", + "6.1\u202fGB" + ], + [ + "8b-23-q5_K_S", + "5.7\u202fGB" + ], + [ + "8b-23-q5_K_M", + "5.8\u202fGB" + ], + [ + "8b-23-q6_K", + "6.6\u202fGB" + ], + [ + "8b-23-q8_0", + "8.5\u202fGB" + ], + [ + "35b-23-q2_K", + "14\u202fGB" + ], + [ + "35b-23-q3_K_S", + "16\u202fGB" + ], + [ + "35b-23-q3_K_M", + "18\u202fGB" + ], + [ + "35b-23-q3_K_L", + "19\u202fGB" + ], + [ + "35b-23-q4_0", + "20\u202fGB" + ], + [ + "35b-23-q4_1", + "22\u202fGB" + ], + [ + "35b-23-q4_K_S", + "20\u202fGB" + ], + [ + "35b-23-q4_K_M", + "22\u202fGB" + ], + [ + "35b-23-q5_0", + "24\u202fGB" + ], + [ + "35b-23-q5_1", + "26\u202fGB" + ], + [ + "35b-23-q5_K_S", + "24\u202fGB" + ], + [ + "35b-23-q5_K_M", + "25\u202fGB" + ], + [ + "35b-23-q6_K", + "29\u202fGB" + ], + [ + "35b-23-q8_0", + "37\u202fGB" + ] + ], + "image": false, + "author": "Cohere" + }, + "wizardlm2": { + "url": "https://ollama.com/library/wizardlm2", + "description": "State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.", + "tags": [ + [ + "latest", + "4.1\u202fGB" + ], + [ + "7b", + "4.1\u202fGB" + ], + [ + "8x22b", + "80\u202fGB" + ], + [ + "7b-fp16", + "14\u202fGB" + ], + [ + "7b-q2_K", + "2.7\u202fGB" + ], + [ + "7b-q3_K_S", + "3.2\u202fGB" + ], + [ + "7b-q3_K_M", + "3.5\u202fGB" + ], + [ + "7b-q3_K_L", + "3.8\u202fGB" + ], + [ + "7b-q4_0", + "4.1\u202fGB" + ], + [ + "7b-q4_1", + "4.6\u202fGB" + ], + [ + "7b-q4_K_S", + "4.1\u202fGB" + ], + [ + "7b-q4_K_M", + "4.4\u202fGB" + ], + [ + "7b-q5_0", + "5.0\u202fGB" + ], + [ + "7b-q5_1", + "5.4\u202fGB" + ], + [ + "7b-q5_K_S", + "5.0\u202fGB" + ], + [ + "7b-q5_K_M", + "5.1\u202fGB" + ], + [ + "7b-q6_K", + "5.9\u202fGB" + ], + [ + "7b-q8_0", + "7.7\u202fGB" + ], + [ + "8x22b-fp16", + "281\u202fGB" + ], + [ + "8x22b-q2_K", + "52\u202fGB" + ], + [ + "8x22b-q4_0", + "80\u202fGB" + ], + [ + "8x22b-q8_0", + "149\u202fGB" + ] + ], + "image": false, + "author": "Microsoft" + }, + "codeqwen": { + "url": "https://ollama.com/library/codeqwen", + "description": "CodeQwen1.5 is a large language model pretrained on a large amount of code data.", + "tags": [ + [ + "latest", + "4.2\u202fGB" + ], + [ + "7b", + "4.2\u202fGB" + ], + [ + "chat", + "4.2\u202fGB" + ], + [ + "code", + "4.2\u202fGB" + ], + [ + "v1.5", + "4.2\u202fGB" + ], + [ + "v1.5-chat", + "4.2\u202fGB" + ], + [ + "v1.5-code", + "4.2\u202fGB" + ], + [ + "7b-chat", + "4.2\u202fGB" + ], + [ + "7b-code", + "4.2\u202fGB" + ], + [ + "7b-chat-v1.5-fp16", + "15\u202fGB" + ], + [ + "7b-chat-v1.5-q2_K", + "3.1\u202fGB" + ], + [ + "7b-chat-v1.5-q3_K_S", + "3.5\u202fGB" + ], + [ + "7b-chat-v1.5-q3_K_M", + "3.8\u202fGB" + ], + [ + "7b-chat-v1.5-q3_K_L", + "4.0\u202fGB" + ], + [ + "7b-chat-v1.5-q4_0", + "4.2\u202fGB" + ], + [ + "7b-chat-v1.5-q4_1", + "4.6\u202fGB" + ], + [ + "7b-chat-v1.5-q4_K_S", + "4.4\u202fGB" + ], + [ + "7b-chat-v1.5-q4_K_M", + "4.7\u202fGB" + ], + [ + "7b-chat-v1.5-q5_0", + "5.0\u202fGB" + ], + [ + "7b-chat-v1.5-q5_1", + "5.5\u202fGB" + ], + [ + "7b-chat-v1.5-q5_K_S", + "5.1\u202fGB" + ], + [ + "7b-chat-v1.5-q5_K_M", + "5.4\u202fGB" + ], + [ + "7b-chat-v1.5-q6_K", + "6.4\u202fGB" + ], + [ + "7b-chat-v1.5-q8_0", + "7.7\u202fGB" + ], + [ + "7b-code-v1.5-fp16", + "15\u202fGB" + ], + [ + "7b-code-v1.5-q4_0", + "4.2\u202fGB" + ], + [ + "7b-code-v1.5-q4_1", + "4.6\u202fGB" + ], + [ + "7b-code-v1.5-q5_0", + "5.0\u202fGB" + ], + [ + "7b-code-v1.5-q5_1", + "5.5\u202fGB" + ], + [ + "7b-code-v1.5-q8_0", + "7.7\u202fGB" + ] + ], + "image": false, + "author": "Alibaba" + }, + "tinydolphin": { + "url": "https://ollama.com/library/tinydolphin", + "description": "An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.", + "tags": [ + [ + "latest", + "637\u202fMB" + ], + [ + "1.1b", + "637\u202fMB" + ], + [ + "v2.8", + "637\u202fMB" + ], + [ + "1.1b-v2.8-fp16", + "2.2\u202fGB" + ], + [ + "1.1b-v2.8-q2_K", + "432\u202fMB" + ], + [ + "1.1b-v2.8-q3_K_S", + "499\u202fMB" + ], + [ + "1.1b-v2.8-q3_K_M", + "548\u202fMB" + ], + [ + "1.1b-v2.8-q3_K_L", + "592\u202fMB" + ], + [ + "1.1b-v2.8-q4_0", + "637\u202fMB" + ], + [ + "1.1b-v2.8-q4_1", + "701\u202fMB" + ], + [ + "1.1b-v2.8-q4_K_S", + "640\u202fMB" + ], + [ + "1.1b-v2.8-q4_K_M", + "668\u202fMB" + ], + [ + "1.1b-v2.8-q5_0", + "766\u202fMB" + ], + [ + "1.1b-v2.8-q5_1", + "831\u202fMB" + ], + [ + "1.1b-v2.8-q5_K_S", + "766\u202fMB" + ], + [ + "1.1b-v2.8-q5_K_M", + "782\u202fMB" + ], + [ + "1.1b-v2.8-q6_K", + "903\u202fMB" + ], + [ + "1.1b-v2.8-q8_0", + "1.2\u202fGB" + ] + ], + "image": false, + "author": "Eric Hartford" + }, + "all-minilm": { + "url": "https://ollama.com/library/all-minilm", + "description": "Embedding models on very large sentence level datasets.", + "tags": [ + [ + "latest", + "46\u202fMB" + ], + [ + "22m", + "46\u202fMB" + ], + [ + "33m", + "67\u202fMB" + ], + [ + "l12", + "67\u202fMB" + ], + [ + "l12-v2", + "67\u202fMB" + ], + [ + "l6", + "46\u202fMB" + ], + [ + "l6-v2", + "46\u202fMB" + ], + [ + "v2", + "46\u202fMB" + ], + [ + "22m-l6-v2-fp16", + "46\u202fMB" + ], + [ + "33m-l12-v2-fp16", + "67\u202fMB" + ] + ], + "image": false, + "author": "Sentence Transformers" + }, "wizardcoder": { "url": "https://ollama.com/library/wizardcoder", "description": "State-of-the-art code generation model", @@ -13671,181 +14683,81 @@ "image": false, "author": "Teknium" }, - "all-minilm": { - "url": "https://ollama.com/library/all-minilm", - "description": "Embedding models on very large sentence level datasets.", + "bakllava": { + "url": "https://ollama.com/library/bakllava", + "description": "BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.", "tags": [ [ "latest", - "46\u202fMB" - ], - [ - "22m", - "46\u202fMB" - ], - [ - "33m", - "67\u202fMB" - ], - [ - "l12", - "67\u202fMB" - ], - [ - "l12-v2", - "67\u202fMB" - ], - [ - "l6", - "46\u202fMB" - ], - [ - "l6-v2", - "46\u202fMB" - ], - [ - "v2", - "46\u202fMB" - ], - [ - "22m-l6-v2-fp16", - "46\u202fMB" - ], - [ - "33m-l12-v2-fp16", - "67\u202fMB" - ] - ], - "image": false, - "author": "Sentence Transformers" - }, - "codeqwen": { - "url": "https://ollama.com/library/codeqwen", - "description": "CodeQwen1.5 is a large language model pretrained on a large amount of code data.", - "tags": [ - [ - "latest", - "4.2\u202fGB" - ], - [ - "7b", - "4.2\u202fGB" - ], - [ - "chat", - "4.2\u202fGB" - ], - [ - "code", - "4.2\u202fGB" - ], - [ - "v1.5", - "4.2\u202fGB" - ], - [ - "v1.5-chat", - "4.2\u202fGB" - ], - [ - "v1.5-code", - "4.2\u202fGB" - ], - [ - "7b-chat", - "4.2\u202fGB" - ], - [ - "7b-code", - "4.2\u202fGB" - ], - [ - "7b-chat-v1.5-fp16", - "15\u202fGB" - ], - [ - "7b-chat-v1.5-q2_K", - "3.1\u202fGB" - ], - [ - "7b-chat-v1.5-q3_K_S", - "3.5\u202fGB" - ], - [ - "7b-chat-v1.5-q3_K_M", - "3.8\u202fGB" - ], - [ - "7b-chat-v1.5-q3_K_L", - "4.0\u202fGB" - ], - [ - "7b-chat-v1.5-q4_0", - "4.2\u202fGB" - ], - [ - "7b-chat-v1.5-q4_1", - "4.6\u202fGB" - ], - [ - "7b-chat-v1.5-q4_K_S", - "4.4\u202fGB" - ], - [ - "7b-chat-v1.5-q4_K_M", "4.7\u202fGB" ], [ - "7b-chat-v1.5-q5_0", - "5.0\u202fGB" + "7b", + "4.7\u202fGB" ], [ - "7b-chat-v1.5-q5_1", - "5.5\u202fGB" - ], - [ - "7b-chat-v1.5-q5_K_S", - "5.1\u202fGB" - ], - [ - "7b-chat-v1.5-q5_K_M", - "5.4\u202fGB" - ], - [ - "7b-chat-v1.5-q6_K", - "6.4\u202fGB" - ], - [ - "7b-chat-v1.5-q8_0", - "7.7\u202fGB" - ], - [ - "7b-code-v1.5-fp16", + "7b-v1-fp16", "15\u202fGB" ], [ - "7b-code-v1.5-q4_0", - "4.2\u202fGB" + "7b-v1-q2_K", + "3.7\u202fGB" ], [ - "7b-code-v1.5-q4_1", - "4.6\u202fGB" + "7b-v1-q3_K_S", + "3.8\u202fGB" ], [ - "7b-code-v1.5-q5_0", + "7b-v1-q3_K_M", + "4.1\u202fGB" + ], + [ + "7b-v1-q3_K_L", + "4.4\u202fGB" + ], + [ + "7b-v1-q4_0", + "4.7\u202fGB" + ], + [ + "7b-v1-q4_1", + "5.2\u202fGB" + ], + [ + "7b-v1-q4_K_S", + "4.8\u202fGB" + ], + [ + "7b-v1-q4_K_M", "5.0\u202fGB" ], [ - "7b-code-v1.5-q5_1", - "5.5\u202fGB" + "7b-v1-q5_0", + "5.6\u202fGB" ], [ - "7b-code-v1.5-q8_0", - "7.7\u202fGB" + "7b-v1-q5_1", + "6.1\u202fGB" + ], + [ + "7b-v1-q5_K_S", + "5.6\u202fGB" + ], + [ + "7b-v1-q5_K_M", + "5.8\u202fGB" + ], + [ + "7b-v1-q6_K", + "6.6\u202fGB" + ], + [ + "7b-v1-q8_0", + "8.3\u202fGB" ] ], - "image": false, - "author": "Alibaba" + "image": true, + "author": "Skunkworks AI" }, "stablelm2": { "url": "https://ollama.com/library/stablelm2", @@ -14191,6 +15103,222 @@ "image": false, "author": "Stability AI" }, + "qwen2-math": { + "url": "https://ollama.com/library/qwen2-math", + "description": "Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o).", + "tags": [ + [ + "latest", + "4.4\u202fGB" + ], + [ + "1.5b", + "935\u202fMB" + ], + [ + "7b", + "4.4\u202fGB" + ], + [ + "72b", + "41\u202fGB" + ], + [ + "1.5b-instruct", + "935\u202fMB" + ], + [ + "7b-instruct", + "4.4\u202fGB" + ], + [ + "72b-instruct", + "41\u202fGB" + ], + [ + "1.5b-instruct-fp16", + "3.1\u202fGB" + ], + [ + "1.5b-instruct-q2_K", + "676\u202fMB" + ], + [ + "1.5b-instruct-q3_K_S", + "761\u202fMB" + ], + [ + "1.5b-instruct-q3_K_M", + "824\u202fMB" + ], + [ + "1.5b-instruct-q3_K_L", + "880\u202fMB" + ], + [ + "1.5b-instruct-q4_0", + "935\u202fMB" + ], + [ + "1.5b-instruct-q4_1", + "1.0\u202fGB" + ], + [ + "1.5b-instruct-q4_K_S", + "940\u202fMB" + ], + [ + "1.5b-instruct-q4_K_M", + "986\u202fMB" + ], + [ + "1.5b-instruct-q5_0", + "1.1\u202fGB" + ], + [ + "1.5b-instruct-q5_1", + "1.2\u202fGB" + ], + [ + "1.5b-instruct-q5_K_S", + "1.1\u202fGB" + ], + [ + "1.5b-instruct-q5_K_M", + "1.1\u202fGB" + ], + [ + "1.5b-instruct-q6_K", + "1.3\u202fGB" + ], + [ + "1.5b-instruct-q8_0", + "1.6\u202fGB" + ], + [ + "7b-instruct-fp16", + "15\u202fGB" + ], + [ + "7b-instruct-q2_K", + "3.0\u202fGB" + ], + [ + "7b-instruct-q3_K_S", + "3.5\u202fGB" + ], + [ + "7b-instruct-q3_K_M", + "3.8\u202fGB" + ], + [ + "7b-instruct-q3_K_L", + "4.1\u202fGB" + ], + [ + "7b-instruct-q4_0", + "4.4\u202fGB" + ], + [ + "7b-instruct-q4_1", + "4.9\u202fGB" + ], + [ + "7b-instruct-q4_K_S", + "4.5\u202fGB" + ], + [ + "7b-instruct-q4_K_M", + "4.7\u202fGB" + ], + [ + "7b-instruct-q5_0", + "5.3\u202fGB" + ], + [ + "7b-instruct-q5_1", + "5.8\u202fGB" + ], + [ + "7b-instruct-q5_K_S", + "5.3\u202fGB" + ], + [ + "7b-instruct-q5_K_M", + "5.4\u202fGB" + ], + [ + "7b-instruct-q6_K", + "6.3\u202fGB" + ], + [ + "7b-instruct-q8_0", + "8.1\u202fGB" + ], + [ + "72b-instruct-fp16", + "145\u202fGB" + ], + [ + "72b-instruct-q2_K", + "30\u202fGB" + ], + [ + "72b-instruct-q3_K_S", + "34\u202fGB" + ], + [ + "72b-instruct-q3_K_M", + "38\u202fGB" + ], + [ + "72b-instruct-q3_K_L", + "40\u202fGB" + ], + [ + "72b-instruct-q4_0", + "41\u202fGB" + ], + [ + "72b-instruct-q4_1", + "46\u202fGB" + ], + [ + "72b-instruct-q4_K_S", + "44\u202fGB" + ], + [ + "72b-instruct-q4_K_M", + "47\u202fGB" + ], + [ + "72b-instruct-q5_0", + "50\u202fGB" + ], + [ + "72b-instruct-q5_1", + "55\u202fGB" + ], + [ + "72b-instruct-q5_K_S", + "51\u202fGB" + ], + [ + "72b-instruct-q5_K_M", + "54\u202fGB" + ], + [ + "72b-instruct-q6_K", + "64\u202fGB" + ], + [ + "72b-instruct-q8_0", + "77\u202fGB" + ] + ], + "image": false, + "author": "Alibaba" + }, "wizard-math": { "url": "https://ollama.com/library/wizard-math", "description": "Model focused on math and logic problems", @@ -14455,6 +15583,154 @@ "image": false, "author": "WizardLM Team" }, + "llama3-gradient": { + "url": "https://ollama.com/library/llama3-gradient", + "description": "This model extends LLama-3 8B's context length from 8k to over 1m tokens.", + "tags": [ + [ + "latest", + "4.7\u202fGB" + ], + [ + "1048k", + "4.7\u202fGB" + ], + [ + "8b", + "4.7\u202fGB" + ], + [ + "70b", + "40\u202fGB" + ], + [ + "instruct", + "4.7\u202fGB" + ], + [ + "8b-instruct-1048k-fp16", + "16\u202fGB" + ], + [ + "8b-instruct-1048k-q2_K", + "3.2\u202fGB" + ], + [ + "8b-instruct-1048k-q3_K_S", + "3.7\u202fGB" + ], + [ + "8b-instruct-1048k-q3_K_M", + "4.0\u202fGB" + ], + [ + "8b-instruct-1048k-q3_K_L", + "4.3\u202fGB" + ], + [ + "8b-instruct-1048k-q4_0", + "4.7\u202fGB" + ], + [ + "8b-instruct-1048k-q4_1", + "5.1\u202fGB" + ], + [ + "8b-instruct-1048k-q4_K_S", + "4.7\u202fGB" + ], + [ + "8b-instruct-1048k-q4_K_M", + "4.9\u202fGB" + ], + [ + "8b-instruct-1048k-q5_0", + "5.6\u202fGB" + ], + [ + "8b-instruct-1048k-q5_1", + "6.1\u202fGB" + ], + [ + "8b-instruct-1048k-q5_K_S", + "5.6\u202fGB" + ], + [ + "8b-instruct-1048k-q5_K_M", + "5.7\u202fGB" + ], + [ + "8b-instruct-1048k-q6_K", + "6.6\u202fGB" + ], + [ + "8b-instruct-1048k-q8_0", + "8.5\u202fGB" + ], + [ + "70b-instruct-1048k-fp16", + "141\u202fGB" + ], + [ + "70b-instruct-1048k-q2_K", + "26\u202fGB" + ], + [ + "70b-instruct-1048k-q3_K_S", + "31\u202fGB" + ], + [ + "70b-instruct-1048k-q3_K_M", + "34\u202fGB" + ], + [ + "70b-instruct-1048k-q3_K_L", + "37\u202fGB" + ], + [ + "70b-instruct-1048k-q4_0", + "40\u202fGB" + ], + [ + "70b-instruct-1048k-q4_1", + "44\u202fGB" + ], + [ + "70b-instruct-1048k-q4_K_S", + "40\u202fGB" + ], + [ + "70b-instruct-1048k-q4_K_M", + "43\u202fGB" + ], + [ + "70b-instruct-1048k-q5_0", + "49\u202fGB" + ], + [ + "70b-instruct-1048k-q5_1", + "53\u202fGB" + ], + [ + "70b-instruct-1048k-q5_K_S", + "49\u202fGB" + ], + [ + "70b-instruct-1048k-q5_K_M", + "50\u202fGB" + ], + [ + "70b-instruct-1048k-q6_K", + "58\u202fGB" + ], + [ + "70b-instruct-1048k-q8_0", + "75\u202fGB" + ] + ], + "image": false, + "author": "Gradient AI" + }, "neural-chat": { "url": "https://ollama.com/library/neural-chat", "description": "A fine-tuned model based on Mistral with good coverage of domain and language.", @@ -14663,153 +15939,269 @@ "image": false, "author": "Intel" }, - "llama3-gradient": { - "url": "https://ollama.com/library/llama3-gradient", - "description": "This model extends LLama-3 8B's context length from 8k to over 1m tokens.", + "deepseek-llm": { + "url": "https://ollama.com/library/deepseek-llm", + "description": "An advanced language model crafted with 2 trillion bilingual tokens.", "tags": [ [ "latest", - "4.7\u202fGB" - ], - [ - "1048k", - "4.7\u202fGB" - ], - [ - "8b", - "4.7\u202fGB" - ], - [ - "70b", - "40\u202fGB" - ], - [ - "instruct", - "4.7\u202fGB" - ], - [ - "8b-instruct-1048k-fp16", - "16\u202fGB" - ], - [ - "8b-instruct-1048k-q2_K", - "3.2\u202fGB" - ], - [ - "8b-instruct-1048k-q3_K_S", - "3.7\u202fGB" - ], - [ - "8b-instruct-1048k-q3_K_M", "4.0\u202fGB" ], [ - "8b-instruct-1048k-q3_K_L", - "4.3\u202fGB" + "7b", + "4.0\u202fGB" ], [ - "8b-instruct-1048k-q4_0", - "4.7\u202fGB" + "67b", + "38\u202fGB" ], [ - "8b-instruct-1048k-q4_1", - "5.1\u202fGB" + "7b-base", + "4.0\u202fGB" ], [ - "8b-instruct-1048k-q4_K_S", - "4.7\u202fGB" + "7b-chat", + "4.0\u202fGB" ], [ - "8b-instruct-1048k-q4_K_M", + "67b-base", + "38\u202fGB" + ], + [ + "67b-chat", + "38\u202fGB" + ], + [ + "7b-base-fp16", + "14\u202fGB" + ], + [ + "7b-base-q2_K", + "3.0\u202fGB" + ], + [ + "7b-base-q3_K_S", + "3.1\u202fGB" + ], + [ + "7b-base-q3_K_M", + "3.5\u202fGB" + ], + [ + "7b-base-q3_K_L", + "3.7\u202fGB" + ], + [ + "7b-base-q4_0", + "4.0\u202fGB" + ], + [ + "7b-base-q4_1", + "4.4\u202fGB" + ], + [ + "7b-base-q4_K_S", + "4.0\u202fGB" + ], + [ + "7b-base-q4_K_M", + "4.2\u202fGB" + ], + [ + "7b-base-q5_0", + "4.8\u202fGB" + ], + [ + "7b-base-q5_1", + "5.2\u202fGB" + ], + [ + "7b-base-q5_K_S", + "4.8\u202fGB" + ], + [ + "7b-base-q5_K_M", "4.9\u202fGB" ], [ - "8b-instruct-1048k-q5_0", - "5.6\u202fGB" - ], - [ - "8b-instruct-1048k-q5_1", - "6.1\u202fGB" - ], - [ - "8b-instruct-1048k-q5_K_S", - "5.6\u202fGB" - ], - [ - "8b-instruct-1048k-q5_K_M", + "7b-base-q6_K", "5.7\u202fGB" ], [ - "8b-instruct-1048k-q6_K", - "6.6\u202fGB" + "7b-base-q8_0", + "7.3\u202fGB" ], [ - "8b-instruct-1048k-q8_0", - "8.5\u202fGB" + "7b-chat-fp16", + "14\u202fGB" ], [ - "70b-instruct-1048k-fp16", - "141\u202fGB" + "7b-chat-q2_K", + "3.0\u202fGB" ], [ - "70b-instruct-1048k-q2_K", - "26\u202fGB" + "7b-chat-q3_K_S", + "3.1\u202fGB" ], [ - "70b-instruct-1048k-q3_K_S", - "31\u202fGB" + "7b-chat-q3_K_M", + "3.5\u202fGB" ], [ - "70b-instruct-1048k-q3_K_M", - "34\u202fGB" + "7b-chat-q3_K_L", + "3.7\u202fGB" ], [ - "70b-instruct-1048k-q3_K_L", - "37\u202fGB" + "7b-chat-q4_0", + "4.0\u202fGB" ], [ - "70b-instruct-1048k-q4_0", + "7b-chat-q4_1", + "4.4\u202fGB" + ], + [ + "7b-chat-q4_K_S", + "4.0\u202fGB" + ], + [ + "7b-chat-q4_K_M", + "4.2\u202fGB" + ], + [ + "7b-chat-q5_0", + "4.8\u202fGB" + ], + [ + "7b-chat-q5_1", + "5.2\u202fGB" + ], + [ + "7b-chat-q5_K_S", + "4.8\u202fGB" + ], + [ + "7b-chat-q5_K_M", + "4.9\u202fGB" + ], + [ + "7b-chat-q6_K", + "5.7\u202fGB" + ], + [ + "7b-chat-q8_0", + "7.3\u202fGB" + ], + [ + "67b-base-fp16", + "135\u202fGB" + ], + [ + "67b-base-q2_K", + "28\u202fGB" + ], + [ + "67b-base-q3_K_S", + "29\u202fGB" + ], + [ + "67b-base-q3_K_M", + "33\u202fGB" + ], + [ + "67b-base-q3_K_L", + "36\u202fGB" + ], + [ + "67b-base-q4_0", + "38\u202fGB" + ], + [ + "67b-base-q4_1", + "42\u202fGB" + ], + [ + "67b-base-q4_K_S", + "38\u202fGB" + ], + [ + "67b-base-q4_K_M", "40\u202fGB" ], [ - "70b-instruct-1048k-q4_1", - "44\u202fGB" + "67b-base-q5_0", + "46\u202fGB" ], [ - "70b-instruct-1048k-q4_K_S", + "67b-base-q5_1", + "51\u202fGB" + ], + [ + "67b-base-q5_K_S", + "46\u202fGB" + ], + [ + "67b-base-q5_K_M", + "48\u202fGB" + ], + [ + "67b-base-q6_K", + "55\u202fGB" + ], + [ + "67b-base-q8_0", + "72\u202fGB" + ], + [ + "67b-chat-fp16", + "135\u202fGB" + ], + [ + "67b-chat-q2_K", + "28\u202fGB" + ], + [ + "67b-chat-q3_K_S", + "29\u202fGB" + ], + [ + "67b-chat-q3_K_M", + "33\u202fGB" + ], + [ + "67b-chat-q3_K_L", + "36\u202fGB" + ], + [ + "67b-chat-q4_0", + "38\u202fGB" + ], + [ + "67b-chat-q4_1", + "42\u202fGB" + ], + [ + "67b-chat-q4_K_S", + "38\u202fGB" + ], + [ + "67b-chat-q4_K_M", "40\u202fGB" ], [ - "70b-instruct-1048k-q4_K_M", - "43\u202fGB" + "67b-chat-q5_0", + "46\u202fGB" ], [ - "70b-instruct-1048k-q5_0", - "49\u202fGB" + "67b-chat-q5_1", + "51\u202fGB" ], [ - "70b-instruct-1048k-q5_1", - "53\u202fGB" - ], - [ - "70b-instruct-1048k-q5_K_S", - "49\u202fGB" - ], - [ - "70b-instruct-1048k-q5_K_M", - "50\u202fGB" - ], - [ - "70b-instruct-1048k-q6_K", - "58\u202fGB" - ], - [ - "70b-instruct-1048k-q8_0", - "75\u202fGB" + "67b-chat-q5_K_S", + "46\u202fGB" ] ], "image": false, - "author": "Gradient AI" + "author": "DeepSeek Team" }, "phind-codellama": { "url": "https://ollama.com/library/phind-codellama", @@ -15275,354 +16667,6 @@ "image": false, "author": "Nous Research" }, - "dolphincoder": { - "url": "https://ollama.com/library/dolphincoder", - "description": "A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.", - "tags": [ - [ - "latest", - "4.2\u202fGB" - ], - [ - "7b", - "4.2\u202fGB" - ], - [ - "15b", - "9.1\u202fGB" - ], - [ - "7b-starcoder2", - "4.2\u202fGB" - ], - [ - "15b-starcoder2", - "9.1\u202fGB" - ], - [ - "7b-starcoder2-fp16", - "15\u202fGB" - ], - [ - "7b-starcoder2-q2_K", - "2.9\u202fGB" - ], - [ - "7b-starcoder2-q3_K_S", - "3.3\u202fGB" - ], - [ - "7b-starcoder2-q3_K_M", - "3.8\u202fGB" - ], - [ - "7b-starcoder2-q3_K_L", - "4.2\u202fGB" - ], - [ - "7b-starcoder2-q4_0", - "4.2\u202fGB" - ], - [ - "7b-starcoder2-q4_1", - "4.7\u202fGB" - ], - [ - "7b-starcoder2-q4_K_S", - "4.3\u202fGB" - ], - [ - "7b-starcoder2-q4_K_M", - "4.6\u202fGB" - ], - [ - "7b-starcoder2-q5_0", - "5.1\u202fGB" - ], - [ - "7b-starcoder2-q5_1", - "5.6\u202fGB" - ], - [ - "7b-starcoder2-q5_K_S", - "5.1\u202fGB" - ], - [ - "7b-starcoder2-q5_K_M", - "5.3\u202fGB" - ], - [ - "7b-starcoder2-q6_K", - "6.1\u202fGB" - ], - [ - "7b-starcoder2-q8_0", - "7.9\u202fGB" - ], - [ - "15b-starcoder2-fp16", - "32\u202fGB" - ], - [ - "15b-starcoder2-q2_K", - "6.2\u202fGB" - ], - [ - "15b-starcoder2-q3_K_S", - "7.0\u202fGB" - ], - [ - "15b-starcoder2-q3_K_M", - "8.1\u202fGB" - ], - [ - "15b-starcoder2-q3_K_L", - "9.0\u202fGB" - ], - [ - "15b-starcoder2-q4_0", - "9.1\u202fGB" - ], - [ - "15b-starcoder2-q4_1", - "10\u202fGB" - ], - [ - "15b-starcoder2-q4_K_S", - "9.3\u202fGB" - ], - [ - "15b-starcoder2-q4_K_M", - "9.9\u202fGB" - ], - [ - "15b-starcoder2-q5_0", - "11\u202fGB" - ], - [ - "15b-starcoder2-q5_1", - "12\u202fGB" - ], - [ - "15b-starcoder2-q5_K_S", - "11\u202fGB" - ], - [ - "15b-starcoder2-q5_K_M", - "11\u202fGB" - ], - [ - "15b-starcoder2-q6_K", - "13\u202fGB" - ], - [ - "15b-starcoder2-q8_0", - "17\u202fGB" - ] - ], - "image": false, - "author": "Cognitive Computations" - }, - "sqlcoder": { - "url": "https://ollama.com/library/sqlcoder", - "description": "SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks", - "tags": [ - [ - "latest", - "4.1\u202fGB" - ], - [ - "7b", - "4.1\u202fGB" - ], - [ - "15b", - "9.0\u202fGB" - ], - [ - "7b-fp16", - "14\u202fGB" - ], - [ - "7b-q2_K", - "3.1\u202fGB" - ], - [ - "7b-q3_K_S", - "3.2\u202fGB" - ], - [ - "7b-q3_K_M", - "3.5\u202fGB" - ], - [ - "7b-q3_K_L", - "3.8\u202fGB" - ], - [ - "7b-q4_0", - "4.1\u202fGB" - ], - [ - "7b-q4_1", - "4.6\u202fGB" - ], - [ - "7b-q4_K_S", - "4.1\u202fGB" - ], - [ - "7b-q4_K_M", - "4.4\u202fGB" - ], - [ - "7b-q5_0", - "5.0\u202fGB" - ], - [ - "7b-q5_1", - "5.4\u202fGB" - ], - [ - "7b-q5_K_S", - "5.0\u202fGB" - ], - [ - "7b-q5_K_M", - "5.1\u202fGB" - ], - [ - "7b-q6_K", - "5.9\u202fGB" - ], - [ - "7b-q8_0", - "7.7\u202fGB" - ], - [ - "15b-fp16", - "32\u202fGB" - ], - [ - "15b-q2_K", - "6.7\u202fGB" - ], - [ - "15b-q3_K_S", - "6.9\u202fGB" - ], - [ - "15b-q3_K_M", - "8.2\u202fGB" - ], - [ - "15b-q3_K_L", - "9.1\u202fGB" - ], - [ - "15b-q4_0", - "9.0\u202fGB" - ], - [ - "15b-q4_1", - "10.0\u202fGB" - ], - [ - "15b-q4_K_S", - "9.1\u202fGB" - ], - [ - "15b-q4_K_M", - "10.0\u202fGB" - ], - [ - "15b-q5_0", - "11\u202fGB" - ], - [ - "15b-q5_1", - "12\u202fGB" - ], - [ - "15b-q5_K_S", - "11\u202fGB" - ], - [ - "15b-q5_K_M", - "12\u202fGB" - ], - [ - "15b-q6_K", - "13\u202fGB" - ], - [ - "15b-q8_0", - "17\u202fGB" - ], - [ - "70b-alpha-fp16", - "138\u202fGB" - ], - [ - "70b-alpha-q2_K", - "25\u202fGB" - ], - [ - "70b-alpha-q3_K_S", - "30\u202fGB" - ], - [ - "70b-alpha-q3_K_M", - "33\u202fGB" - ], - [ - "70b-alpha-q3_K_L", - "36\u202fGB" - ], - [ - "70b-alpha-q4_0", - "39\u202fGB" - ], - [ - "70b-alpha-q4_1", - "43\u202fGB" - ], - [ - "70b-alpha-q4_K_S", - "39\u202fGB" - ], - [ - "70b-alpha-q4_K_M", - "41\u202fGB" - ], - [ - "70b-alpha-q5_0", - "47\u202fGB" - ], - [ - "70b-alpha-q5_1", - "52\u202fGB" - ], - [ - "70b-alpha-q5_K_S", - "47\u202fGB" - ], - [ - "70b-alpha-q5_K_M", - "49\u202fGB" - ], - [ - "70b-alpha-q6_K", - "57\u202fGB" - ], - [ - "70b-alpha-q8_0", - "73\u202fGB" - ] - ], - "image": false, - "author": "Defog.ai" - }, "xwinlm": { "url": "https://ollama.com/library/xwinlm", "description": "Conversational model based on Llama 2 that performs competitively on various benchmarks.", @@ -15951,269 +16995,501 @@ "image": false, "author": "Xwin LM" }, - "deepseek-llm": { - "url": "https://ollama.com/library/deepseek-llm", - "description": "An advanced language model crafted with 2 trillion bilingual tokens.", + "sqlcoder": { + "url": "https://ollama.com/library/sqlcoder", + "description": "SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks", "tags": [ [ "latest", - "4.0\u202fGB" + "4.1\u202fGB" ], [ "7b", - "4.0\u202fGB" + "4.1\u202fGB" ], [ - "67b", - "38\u202fGB" + "15b", + "9.0\u202fGB" ], [ - "7b-base", - "4.0\u202fGB" - ], - [ - "7b-chat", - "4.0\u202fGB" - ], - [ - "67b-base", - "38\u202fGB" - ], - [ - "67b-chat", - "38\u202fGB" - ], - [ - "7b-base-fp16", + "7b-fp16", "14\u202fGB" ], [ - "7b-base-q2_K", - "3.0\u202fGB" - ], - [ - "7b-base-q3_K_S", + "7b-q2_K", "3.1\u202fGB" ], [ - "7b-base-q3_K_M", + "7b-q3_K_S", + "3.2\u202fGB" + ], + [ + "7b-q3_K_M", "3.5\u202fGB" ], [ - "7b-base-q3_K_L", - "3.7\u202fGB" + "7b-q3_K_L", + "3.8\u202fGB" ], [ - "7b-base-q4_0", - "4.0\u202fGB" + "7b-q4_0", + "4.1\u202fGB" ], [ - "7b-base-q4_1", + "7b-q4_1", + "4.6\u202fGB" + ], + [ + "7b-q4_K_S", + "4.1\u202fGB" + ], + [ + "7b-q4_K_M", "4.4\u202fGB" ], [ - "7b-base-q4_K_S", - "4.0\u202fGB" + "7b-q5_0", + "5.0\u202fGB" ], [ - "7b-base-q4_K_M", - "4.2\u202fGB" + "7b-q5_1", + "5.4\u202fGB" ], [ - "7b-base-q5_0", - "4.8\u202fGB" + "7b-q5_K_S", + "5.0\u202fGB" ], [ - "7b-base-q5_1", - "5.2\u202fGB" + "7b-q5_K_M", + "5.1\u202fGB" ], [ - "7b-base-q5_K_S", - "4.8\u202fGB" + "7b-q6_K", + "5.9\u202fGB" ], [ - "7b-base-q5_K_M", - "4.9\u202fGB" + "7b-q8_0", + "7.7\u202fGB" ], [ - "7b-base-q6_K", - "5.7\u202fGB" + "15b-fp16", + "32\u202fGB" ], [ - "7b-base-q8_0", - "7.3\u202fGB" + "15b-q2_K", + "6.7\u202fGB" ], [ - "7b-chat-fp16", - "14\u202fGB" + "15b-q3_K_S", + "6.9\u202fGB" ], [ - "7b-chat-q2_K", - "3.0\u202fGB" + "15b-q3_K_M", + "8.2\u202fGB" ], [ - "7b-chat-q3_K_S", - "3.1\u202fGB" + "15b-q3_K_L", + "9.1\u202fGB" ], [ - "7b-chat-q3_K_M", - "3.5\u202fGB" + "15b-q4_0", + "9.0\u202fGB" ], [ - "7b-chat-q3_K_L", - "3.7\u202fGB" + "15b-q4_1", + "10.0\u202fGB" ], [ - "7b-chat-q4_0", - "4.0\u202fGB" + "15b-q4_K_S", + "9.1\u202fGB" ], [ - "7b-chat-q4_1", - "4.4\u202fGB" + "15b-q4_K_M", + "10.0\u202fGB" ], [ - "7b-chat-q4_K_S", - "4.0\u202fGB" + "15b-q5_0", + "11\u202fGB" ], [ - "7b-chat-q4_K_M", - "4.2\u202fGB" + "15b-q5_1", + "12\u202fGB" ], [ - "7b-chat-q5_0", - "4.8\u202fGB" + "15b-q5_K_S", + "11\u202fGB" ], [ - "7b-chat-q5_1", - "5.2\u202fGB" + "15b-q5_K_M", + "12\u202fGB" ], [ - "7b-chat-q5_K_S", - "4.8\u202fGB" + "15b-q6_K", + "13\u202fGB" ], [ - "7b-chat-q5_K_M", - "4.9\u202fGB" + "15b-q8_0", + "17\u202fGB" ], [ - "7b-chat-q6_K", - "5.7\u202fGB" + "70b-alpha-fp16", + "138\u202fGB" ], [ - "7b-chat-q8_0", - "7.3\u202fGB" + "70b-alpha-q2_K", + "25\u202fGB" ], [ - "67b-base-fp16", - "135\u202fGB" + "70b-alpha-q3_K_S", + "30\u202fGB" ], [ - "67b-base-q2_K", - "28\u202fGB" - ], - [ - "67b-base-q3_K_S", - "29\u202fGB" - ], - [ - "67b-base-q3_K_M", + "70b-alpha-q3_K_M", "33\u202fGB" ], [ - "67b-base-q3_K_L", + "70b-alpha-q3_K_L", "36\u202fGB" ], [ - "67b-base-q4_0", - "38\u202fGB" + "70b-alpha-q4_0", + "39\u202fGB" ], [ - "67b-base-q4_1", - "42\u202fGB" + "70b-alpha-q4_1", + "43\u202fGB" ], [ - "67b-base-q4_K_S", - "38\u202fGB" + "70b-alpha-q4_K_S", + "39\u202fGB" ], [ - "67b-base-q4_K_M", - "40\u202fGB" + "70b-alpha-q4_K_M", + "41\u202fGB" ], [ - "67b-base-q5_0", - "46\u202fGB" + "70b-alpha-q5_0", + "47\u202fGB" ], [ - "67b-base-q5_1", - "51\u202fGB" + "70b-alpha-q5_1", + "52\u202fGB" ], [ - "67b-base-q5_K_S", - "46\u202fGB" + "70b-alpha-q5_K_S", + "47\u202fGB" ], [ - "67b-base-q5_K_M", - "48\u202fGB" + "70b-alpha-q5_K_M", + "49\u202fGB" ], [ - "67b-base-q6_K", - "55\u202fGB" + "70b-alpha-q6_K", + "57\u202fGB" ], [ - "67b-base-q8_0", - "72\u202fGB" - ], - [ - "67b-chat-fp16", - "135\u202fGB" - ], - [ - "67b-chat-q2_K", - "28\u202fGB" - ], - [ - "67b-chat-q3_K_S", - "29\u202fGB" - ], - [ - "67b-chat-q3_K_M", - "33\u202fGB" - ], - [ - "67b-chat-q3_K_L", - "36\u202fGB" - ], - [ - "67b-chat-q4_0", - "38\u202fGB" - ], - [ - "67b-chat-q4_1", - "42\u202fGB" - ], - [ - "67b-chat-q4_K_S", - "38\u202fGB" - ], - [ - "67b-chat-q4_K_M", - "40\u202fGB" - ], - [ - "67b-chat-q5_0", - "46\u202fGB" - ], - [ - "67b-chat-q5_1", - "51\u202fGB" - ], - [ - "67b-chat-q5_K_S", - "46\u202fGB" + "70b-alpha-q8_0", + "73\u202fGB" ] ], "image": false, - "author": "DeepSeek Team" + "author": "Defog.ai" + }, + "dolphincoder": { + "url": "https://ollama.com/library/dolphincoder", + "description": "A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.", + "tags": [ + [ + "latest", + "4.2\u202fGB" + ], + [ + "7b", + "4.2\u202fGB" + ], + [ + "15b", + "9.1\u202fGB" + ], + [ + "7b-starcoder2", + "4.2\u202fGB" + ], + [ + "15b-starcoder2", + "9.1\u202fGB" + ], + [ + "7b-starcoder2-fp16", + "15\u202fGB" + ], + [ + "7b-starcoder2-q2_K", + "2.9\u202fGB" + ], + [ + "7b-starcoder2-q3_K_S", + "3.3\u202fGB" + ], + [ + "7b-starcoder2-q3_K_M", + "3.8\u202fGB" + ], + [ + "7b-starcoder2-q3_K_L", + "4.2\u202fGB" + ], + [ + "7b-starcoder2-q4_0", + "4.2\u202fGB" + ], + [ + "7b-starcoder2-q4_1", + "4.7\u202fGB" + ], + [ + "7b-starcoder2-q4_K_S", + "4.3\u202fGB" + ], + [ + "7b-starcoder2-q4_K_M", + "4.6\u202fGB" + ], + [ + "7b-starcoder2-q5_0", + "5.1\u202fGB" + ], + [ + "7b-starcoder2-q5_1", + "5.6\u202fGB" + ], + [ + "7b-starcoder2-q5_K_S", + "5.1\u202fGB" + ], + [ + "7b-starcoder2-q5_K_M", + "5.3\u202fGB" + ], + [ + "7b-starcoder2-q6_K", + "6.1\u202fGB" + ], + [ + "7b-starcoder2-q8_0", + "7.9\u202fGB" + ], + [ + "15b-starcoder2-fp16", + "32\u202fGB" + ], + [ + "15b-starcoder2-q2_K", + "6.2\u202fGB" + ], + [ + "15b-starcoder2-q3_K_S", + "7.0\u202fGB" + ], + [ + "15b-starcoder2-q3_K_M", + "8.1\u202fGB" + ], + [ + "15b-starcoder2-q3_K_L", + "9.0\u202fGB" + ], + [ + "15b-starcoder2-q4_0", + "9.1\u202fGB" + ], + [ + "15b-starcoder2-q4_1", + "10\u202fGB" + ], + [ + "15b-starcoder2-q4_K_S", + "9.3\u202fGB" + ], + [ + "15b-starcoder2-q4_K_M", + "9.9\u202fGB" + ], + [ + "15b-starcoder2-q5_0", + "11\u202fGB" + ], + [ + "15b-starcoder2-q5_1", + "12\u202fGB" + ], + [ + "15b-starcoder2-q5_K_S", + "11\u202fGB" + ], + [ + "15b-starcoder2-q5_K_M", + "11\u202fGB" + ], + [ + "15b-starcoder2-q6_K", + "13\u202fGB" + ], + [ + "15b-starcoder2-q8_0", + "17\u202fGB" + ] + ], + "image": false, + "author": "Cognitive Computations" + }, + "llama3-chatqa": { + "url": "https://ollama.com/library/llama3-chatqa", + "description": "A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).", + "tags": [ + [ + "latest", + "4.7\u202fGB" + ], + [ + "8b", + "4.7\u202fGB" + ], + [ + "70b", + "40\u202fGB" + ], + [ + "8b-v1.5", + "4.7\u202fGB" + ], + [ + "70b-v1.5", + "40\u202fGB" + ], + [ + "8b-v1.5-fp16", + "16\u202fGB" + ], + [ + "8b-v1.5-q2_K", + "3.2\u202fGB" + ], + [ + "8b-v1.5-q3_K_S", + "3.7\u202fGB" + ], + [ + "8b-v1.5-q3_K_M", + "4.0\u202fGB" + ], + [ + "8b-v1.5-q3_K_L", + "4.3\u202fGB" + ], + [ + "8b-v1.5-q4_0", + "4.7\u202fGB" + ], + [ + "8b-v1.5-q4_1", + "5.1\u202fGB" + ], + [ + "8b-v1.5-q4_K_S", + "4.7\u202fGB" + ], + [ + "8b-v1.5-q4_K_M", + "4.9\u202fGB" + ], + [ + "8b-v1.5-q5_0", + "5.6\u202fGB" + ], + [ + "8b-v1.5-q5_1", + "6.1\u202fGB" + ], + [ + "8b-v1.5-q5_K_S", + "5.6\u202fGB" + ], + [ + "8b-v1.5-q5_K_M", + "5.7\u202fGB" + ], + [ + "8b-v1.5-q6_K", + "6.6\u202fGB" + ], + [ + "8b-v1.5-q8_0", + "8.5\u202fGB" + ], + [ + "70b-v1.5-fp16", + "141\u202fGB" + ], + [ + "70b-v1.5-q2_K", + "26\u202fGB" + ], + [ + "70b-v1.5-q3_K_S", + "31\u202fGB" + ], + [ + "70b-v1.5-q3_K_M", + "34\u202fGB" + ], + [ + "70b-v1.5-q3_K_L", + "37\u202fGB" + ], + [ + "70b-v1.5-q4_0", + "40\u202fGB" + ], + [ + "70b-v1.5-q4_1", + "44\u202fGB" + ], + [ + "70b-v1.5-q4_K_S", + "40\u202fGB" + ], + [ + "70b-v1.5-q4_K_M", + "43\u202fGB" + ], + [ + "70b-v1.5-q5_0", + "49\u202fGB" + ], + [ + "70b-v1.5-q5_1", + "53\u202fGB" + ], + [ + "70b-v1.5-q5_K_S", + "49\u202fGB" + ], + [ + "70b-v1.5-q5_K_M", + "50\u202fGB" + ], + [ + "70b-v1.5-q6_K", + "58\u202fGB" + ], + [ + "70b-v1.5-q8_0", + "75\u202fGB" + ] + ], + "image": false, + "author": "Nvidia" }, "yarn-llama2": { "url": "https://ollama.com/library/yarn-llama2", @@ -16491,153 +17767,81 @@ "image": false, "author": "Nous Research" }, - "llama3-chatqa": { - "url": "https://ollama.com/library/llama3-chatqa", - "description": "A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).", + "mistral-large": { + "url": "https://ollama.com/library/mistral-large", + "description": "Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and support for dozens of languages.", "tags": [ [ "latest", - "4.7\u202fGB" + "69\u202fGB" ], [ - "8b", - "4.7\u202fGB" + "123b", + "69\u202fGB" ], [ - "70b", - "40\u202fGB" + "123b-instruct-2407-fp16", + "245\u202fGB" ], [ - "8b-v1.5", - "4.7\u202fGB" + "123b-instruct-2407-q2_K", + "45\u202fGB" ], [ - "70b-v1.5", - "40\u202fGB" - ], - [ - "8b-v1.5-fp16", - "16\u202fGB" - ], - [ - "8b-v1.5-q2_K", - "3.2\u202fGB" - ], - [ - "8b-v1.5-q3_K_S", - "3.7\u202fGB" - ], - [ - "8b-v1.5-q3_K_M", - "4.0\u202fGB" - ], - [ - "8b-v1.5-q3_K_L", - "4.3\u202fGB" - ], - [ - "8b-v1.5-q4_0", - "4.7\u202fGB" - ], - [ - "8b-v1.5-q4_1", - "5.1\u202fGB" - ], - [ - "8b-v1.5-q4_K_S", - "4.7\u202fGB" - ], - [ - "8b-v1.5-q4_K_M", - "4.9\u202fGB" - ], - [ - "8b-v1.5-q5_0", - "5.6\u202fGB" - ], - [ - "8b-v1.5-q5_1", - "6.1\u202fGB" - ], - [ - "8b-v1.5-q5_K_S", - "5.6\u202fGB" - ], - [ - "8b-v1.5-q5_K_M", - "5.7\u202fGB" - ], - [ - "8b-v1.5-q6_K", - "6.6\u202fGB" - ], - [ - "8b-v1.5-q8_0", - "8.5\u202fGB" - ], - [ - "70b-v1.5-fp16", - "141\u202fGB" - ], - [ - "70b-v1.5-q2_K", - "26\u202fGB" - ], - [ - "70b-v1.5-q3_K_S", - "31\u202fGB" - ], - [ - "70b-v1.5-q3_K_M", - "34\u202fGB" - ], - [ - "70b-v1.5-q3_K_L", - "37\u202fGB" - ], - [ - "70b-v1.5-q4_0", - "40\u202fGB" - ], - [ - "70b-v1.5-q4_1", - "44\u202fGB" - ], - [ - "70b-v1.5-q4_K_S", - "40\u202fGB" - ], - [ - "70b-v1.5-q4_K_M", - "43\u202fGB" - ], - [ - "70b-v1.5-q5_0", - "49\u202fGB" - ], - [ - "70b-v1.5-q5_1", + "123b-instruct-2407-q3_K_S", "53\u202fGB" ], [ - "70b-v1.5-q5_K_S", - "49\u202fGB" + "123b-instruct-2407-q3_K_M", + "59\u202fGB" ], [ - "70b-v1.5-q5_K_M", - "50\u202fGB" + "123b-instruct-2407-q3_K_L", + "65\u202fGB" ], [ - "70b-v1.5-q6_K", - "58\u202fGB" + "123b-instruct-2407-q4_0", + "69\u202fGB" ], [ - "70b-v1.5-q8_0", - "75\u202fGB" + "123b-instruct-2407-q4_1", + "77\u202fGB" + ], + [ + "123b-instruct-2407-q4_K_S", + "70\u202fGB" + ], + [ + "123b-instruct-2407-q4_K_M", + "73\u202fGB" + ], + [ + "123b-instruct-2407-q5_0", + "84\u202fGB" + ], + [ + "123b-instruct-2407-q5_1", + "92\u202fGB" + ], + [ + "123b-instruct-2407-q5_K_S", + "84\u202fGB" + ], + [ + "123b-instruct-2407-q5_K_M", + "86\u202fGB" + ], + [ + "123b-instruct-2407-q6_K", + "101\u202fGB" + ], + [ + "123b-instruct-2407-q8_0", + "130\u202fGB" ] ], "image": false, - "author": "Nvidia" + "author": "Mistral AI" }, "wizardlm": { "url": "https://ollama.com/library/wizardlm", @@ -16939,866 +18143,6 @@ "image": false, "author": "WizardLM Team" }, - "starling-lm": { - "url": "https://ollama.com/library/starling-lm", - "description": "Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.", - "tags": [ - [ - "latest", - "4.1\u202fGB" - ], - [ - "7b", - "4.1\u202fGB" - ], - [ - "alpha", - "4.1\u202fGB" - ], - [ - "beta", - "4.1\u202fGB" - ], - [ - "7b-alpha", - "4.1\u202fGB" - ], - [ - "7b-beta", - "4.1\u202fGB" - ], - [ - "7b-alpha-fp16", - "14\u202fGB" - ], - [ - "7b-alpha-q2_K", - "2.7\u202fGB" - ], - [ - "7b-alpha-q3_K_S", - "3.2\u202fGB" - ], - [ - "7b-alpha-q3_K_M", - "3.5\u202fGB" - ], - [ - "7b-alpha-q3_K_L", - "3.8\u202fGB" - ], - [ - "7b-alpha-q4_0", - "4.1\u202fGB" - ], - [ - "7b-alpha-q4_1", - "4.6\u202fGB" - ], - [ - "7b-alpha-q4_K_S", - "4.1\u202fGB" - ], - [ - "7b-alpha-q4_K_M", - "4.4\u202fGB" - ], - [ - "7b-alpha-q5_0", - "5.0\u202fGB" - ], - [ - "7b-alpha-q5_1", - "5.4\u202fGB" - ], - [ - "7b-alpha-q5_K_S", - "5.0\u202fGB" - ], - [ - "7b-alpha-q5_K_M", - "5.1\u202fGB" - ], - [ - "7b-alpha-q6_K", - "5.9\u202fGB" - ], - [ - "7b-alpha-q8_0", - "7.7\u202fGB" - ], - [ - "7b-beta-fp16", - "14\u202fGB" - ], - [ - "7b-beta-q2_K", - "2.7\u202fGB" - ], - [ - "7b-beta-q3_K_S", - "3.2\u202fGB" - ], - [ - "7b-beta-q3_K_M", - "3.5\u202fGB" - ], - [ - "7b-beta-q3_K_L", - "3.8\u202fGB" - ], - [ - "7b-beta-q4_0", - "4.1\u202fGB" - ], - [ - "7b-beta-q4_1", - "4.6\u202fGB" - ], - [ - "7b-beta-q4_K_S", - "4.1\u202fGB" - ], - [ - "7b-beta-q4_K_M", - "4.4\u202fGB" - ], - [ - "7b-beta-q5_0", - "5.0\u202fGB" - ], - [ - "7b-beta-q5_1", - "5.4\u202fGB" - ], - [ - "7b-beta-q5_K_S", - "5.0\u202fGB" - ], - [ - "7b-beta-q5_K_M", - "5.1\u202fGB" - ], - [ - "7b-beta-q6_K", - "5.9\u202fGB" - ], - [ - "7b-beta-q8_0", - "7.7\u202fGB" - ] - ], - "image": false, - "author": "Berkeley Nest" - }, - "codegeex4": { - "url": "https://ollama.com/library/codegeex4", - "description": "A versatile model for AI software development scenarios, including code completion.", - "tags": [ - [ - "latest", - "5.5\u202fGB" - ], - [ - "9b", - "5.5\u202fGB" - ], - [ - "9b-all-fp16", - "19\u202fGB" - ], - [ - "9b-all-q2_K", - "4.0\u202fGB" - ], - [ - "9b-all-q3_K_S", - "4.6\u202fGB" - ], - [ - "9b-all-q3_K_M", - "5.1\u202fGB" - ], - [ - "9b-all-q3_K_L", - "5.3\u202fGB" - ], - [ - "9b-all-q4_0", - "5.5\u202fGB" - ], - [ - "9b-all-q4_1", - "6.0\u202fGB" - ], - [ - "9b-all-q4_K_S", - "5.8\u202fGB" - ], - [ - "9b-all-q4_K_M", - "6.3\u202fGB" - ], - [ - "9b-all-q5_0", - "6.6\u202fGB" - ], - [ - "9b-all-q5_1", - "7.1\u202fGB" - ], - [ - "9b-all-q5_K_S", - "6.7\u202fGB" - ], - [ - "9b-all-q5_K_M", - "7.1\u202fGB" - ], - [ - "9b-all-q6_K", - "8.3\u202fGB" - ], - [ - "9b-all-q8_0", - "10.0\u202fGB" - ] - ], - "image": false, - "author": "THUDM" - }, - "snowflake-arctic-embed": { - "url": "https://ollama.com/library/snowflake-arctic-embed", - "description": "A suite of text embedding models by Snowflake, optimized for performance.", - "tags": [ - [ - "latest", - "669\u202fMB" - ], - [ - "22m", - "46\u202fMB" - ], - [ - "33m", - "67\u202fMB" - ], - [ - "110m", - "219\u202fMB" - ], - [ - "137m", - "274\u202fMB" - ], - [ - "335m", - "669\u202fMB" - ], - [ - "l", - "669\u202fMB" - ], - [ - "m", - "219\u202fMB" - ], - [ - "m-long", - "274\u202fMB" - ], - [ - "s", - "67\u202fMB" - ], - [ - "xs", - "46\u202fMB" - ], - [ - "22m-xs-fp16", - "46\u202fMB" - ], - [ - "33m-s-fp16", - "67\u202fMB" - ], - [ - "110m-m-fp16", - "219\u202fMB" - ], - [ - "137m-m-long-fp16", - "274\u202fMB" - ], - [ - "335m-l-fp16", - "669\u202fMB" - ] - ], - "image": false, - "author": "Snowflake" - }, - "orca2": { - "url": "https://ollama.com/library/orca2", - "description": "Orca 2 is built by Microsoft research, and are a fine-tuned version of Meta's Llama 2 models. The model is designed to excel particularly in reasoning.", - "tags": [ - [ - "latest", - "3.8\u202fGB" - ], - [ - "7b", - "3.8\u202fGB" - ], - [ - "13b", - "7.4\u202fGB" - ], - [ - "7b-fp16", - "13\u202fGB" - ], - [ - "7b-q2_K", - "2.8\u202fGB" - ], - [ - "7b-q3_K_S", - "2.9\u202fGB" - ], - [ - "7b-q3_K_M", - "3.3\u202fGB" - ], - [ - "7b-q3_K_L", - "3.6\u202fGB" - ], - [ - "7b-q4_0", - "3.8\u202fGB" - ], - [ - "7b-q4_1", - "4.2\u202fGB" - ], - [ - "7b-q4_K_S", - "3.9\u202fGB" - ], - [ - "7b-q4_K_M", - "4.1\u202fGB" - ], - [ - "7b-q5_0", - "4.7\u202fGB" - ], - [ - "7b-q5_1", - "5.1\u202fGB" - ], - [ - "7b-q5_K_S", - "4.7\u202fGB" - ], - [ - "7b-q5_K_M", - "4.8\u202fGB" - ], - [ - "7b-q6_K", - "5.5\u202fGB" - ], - [ - "7b-q8_0", - "7.2\u202fGB" - ], - [ - "13b-fp16", - "26\u202fGB" - ], - [ - "13b-q2_K", - "5.4\u202fGB" - ], - [ - "13b-q3_K_S", - "5.7\u202fGB" - ], - [ - "13b-q3_K_M", - "6.3\u202fGB" - ], - [ - "13b-q3_K_L", - "6.9\u202fGB" - ], - [ - "13b-q4_0", - "7.4\u202fGB" - ], - [ - "13b-q4_1", - "8.2\u202fGB" - ], - [ - "13b-q4_K_S", - "7.4\u202fGB" - ], - [ - "13b-q4_K_M", - "7.9\u202fGB" - ], - [ - "13b-q5_0", - "9.0\u202fGB" - ], - [ - "13b-q5_1", - "9.8\u202fGB" - ], - [ - "13b-q5_K_S", - "9.0\u202fGB" - ], - [ - "13b-q5_K_M", - "9.2\u202fGB" - ], - [ - "13b-q6_K", - "11\u202fGB" - ], - [ - "13b-q8_0", - "14\u202fGB" - ] - ], - "image": false, - "author": "Microsoft Research" - }, - "solar": { - "url": "https://ollama.com/library/solar", - "description": "A compact, yet powerful 10.7B large language model designed for single-turn conversation.", - "tags": [ - [ - "latest", - "6.1\u202fGB" - ], - [ - "10.7b", - "6.1\u202fGB" - ], - [ - "10.7b-instruct-v1-fp16", - "21\u202fGB" - ], - [ - "10.7b-instruct-v1-q2_K", - "4.5\u202fGB" - ], - [ - "10.7b-instruct-v1-q3_K_S", - "4.7\u202fGB" - ], - [ - "10.7b-instruct-v1-q3_K_M", - "5.2\u202fGB" - ], - [ - "10.7b-instruct-v1-q3_K_L", - "5.7\u202fGB" - ], - [ - "10.7b-instruct-v1-q4_0", - "6.1\u202fGB" - ], - [ - "10.7b-instruct-v1-q4_1", - "6.7\u202fGB" - ], - [ - "10.7b-instruct-v1-q4_K_S", - "6.1\u202fGB" - ], - [ - "10.7b-instruct-v1-q4_K_M", - "6.5\u202fGB" - ], - [ - "10.7b-instruct-v1-q5_0", - "7.4\u202fGB" - ], - [ - "10.7b-instruct-v1-q5_1", - "8.1\u202fGB" - ], - [ - "10.7b-instruct-v1-q5_K_S", - "7.4\u202fGB" - ], - [ - "10.7b-instruct-v1-q5_K_M", - "7.6\u202fGB" - ], - [ - "10.7b-instruct-v1-q6_K", - "8.8\u202fGB" - ], - [ - "10.7b-instruct-v1-q8_0", - "11\u202fGB" - ], - [ - "10.7b-text-v1-fp16", - "21\u202fGB" - ], - [ - "10.7b-text-v1-q2_K", - "4.5\u202fGB" - ], - [ - "10.7b-text-v1-q3_K_S", - "4.7\u202fGB" - ], - [ - "10.7b-text-v1-q3_K_M", - "5.2\u202fGB" - ], - [ - "10.7b-text-v1-q3_K_L", - "5.7\u202fGB" - ], - [ - "10.7b-text-v1-q4_0", - "6.1\u202fGB" - ], - [ - "10.7b-text-v1-q4_1", - "6.7\u202fGB" - ], - [ - "10.7b-text-v1-q4_K_S", - "6.1\u202fGB" - ], - [ - "10.7b-text-v1-q4_K_M", - "6.5\u202fGB" - ], - [ - "10.7b-text-v1-q5_0", - "7.4\u202fGB" - ], - [ - "10.7b-text-v1-q5_1", - "8.1\u202fGB" - ], - [ - "10.7b-text-v1-q5_K_S", - "7.4\u202fGB" - ], - [ - "10.7b-text-v1-q5_K_M", - "7.6\u202fGB" - ], - [ - "10.7b-text-v1-q6_K", - "8.8\u202fGB" - ], - [ - "10.7b-text-v1-q8_0", - "11\u202fGB" - ] - ], - "image": false, - "author": "Upstage" - }, - "samantha-mistral": { - "url": "https://ollama.com/library/samantha-mistral", - "description": "A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.", - "tags": [ - [ - "latest", - "4.1\u202fGB" - ], - [ - "7b", - "4.1\u202fGB" - ], - [ - "7b-text", - "4.1\u202fGB" - ], - [ - "7b-v1.2-text", - "4.1\u202fGB" - ], - [ - "7b-instruct-fp16", - "14\u202fGB" - ], - [ - "7b-instruct-q2_K", - "3.1\u202fGB" - ], - [ - "7b-instruct-q3_K_S", - "3.2\u202fGB" - ], - [ - "7b-instruct-q3_K_M", - "3.5\u202fGB" - ], - [ - "7b-instruct-q3_K_L", - "3.8\u202fGB" - ], - [ - "7b-instruct-q4_0", - "4.1\u202fGB" - ], - [ - "7b-instruct-q4_1", - "4.6\u202fGB" - ], - [ - "7b-instruct-q4_K_S", - "4.1\u202fGB" - ], - [ - "7b-instruct-q4_K_M", - "4.4\u202fGB" - ], - [ - "7b-instruct-q5_0", - "5.0\u202fGB" - ], - [ - "7b-instruct-q5_1", - "5.4\u202fGB" - ], - [ - "7b-instruct-q5_K_S", - "5.0\u202fGB" - ], - [ - "7b-instruct-q5_K_M", - "5.1\u202fGB" - ], - [ - "7b-instruct-q6_K", - "5.9\u202fGB" - ], - [ - "7b-instruct-q8_0", - "7.7\u202fGB" - ], - [ - "7b-text-fp16", - "14\u202fGB" - ], - [ - "7b-text-q2_K", - "3.1\u202fGB" - ], - [ - "7b-text-q3_K_S", - "3.2\u202fGB" - ], - [ - "7b-text-q3_K_M", - "3.5\u202fGB" - ], - [ - "7b-text-q3_K_L", - "3.8\u202fGB" - ], - [ - "7b-text-q4_0", - "4.1\u202fGB" - ], - [ - "7b-text-q4_1", - "4.6\u202fGB" - ], - [ - "7b-text-q4_K_S", - "4.1\u202fGB" - ], - [ - "7b-text-q4_K_M", - "4.4\u202fGB" - ], - [ - "7b-text-q5_0", - "5.0\u202fGB" - ], - [ - "7b-text-q5_1", - "5.4\u202fGB" - ], - [ - "7b-text-q5_K_S", - "5.0\u202fGB" - ], - [ - "7b-text-q5_K_M", - "5.1\u202fGB" - ], - [ - "7b-text-q6_K", - "5.9\u202fGB" - ], - [ - "7b-text-q8_0", - "7.7\u202fGB" - ], - [ - "7b-v1.2-text-fp16", - "14\u202fGB" - ], - [ - "7b-v1.2-text-q2_K", - "3.1\u202fGB" - ], - [ - "7b-v1.2-text-q3_K_S", - "3.2\u202fGB" - ], - [ - "7b-v1.2-text-q3_K_M", - "3.5\u202fGB" - ], - [ - "7b-v1.2-text-q3_K_L", - "3.8\u202fGB" - ], - [ - "7b-v1.2-text-q4_0", - "4.1\u202fGB" - ], - [ - "7b-v1.2-text-q4_1", - "4.6\u202fGB" - ], - [ - "7b-v1.2-text-q4_K_S", - "4.1\u202fGB" - ], - [ - "7b-v1.2-text-q4_K_M", - "4.4\u202fGB" - ], - [ - "7b-v1.2-text-q5_0", - "5.0\u202fGB" - ], - [ - "7b-v1.2-text-q5_1", - "5.4\u202fGB" - ], - [ - "7b-v1.2-text-q5_K_S", - "5.0\u202fGB" - ], - [ - "7b-v1.2-text-q5_K_M", - "5.1\u202fGB" - ], - [ - "7b-v1.2-text-q6_K", - "5.9\u202fGB" - ], - [ - "7b-v1.2-text-q8_0", - "7.7\u202fGB" - ] - ], - "image": false, - "author": "Eric Hartford" - }, - "moondream": { - "url": "https://ollama.com/library/moondream", - "description": "moondream2 is a small vision language model designed to run efficiently on edge devices.", - "tags": [ - [ - "latest", - "1.7\u202fGB" - ], - [ - "1.8b", - "1.7\u202fGB" - ], - [ - "v2", - "1.7\u202fGB" - ], - [ - "1.8b-v2-fp16", - "3.7\u202fGB" - ], - [ - "1.8b-v2-q2_K", - "1.5\u202fGB" - ], - [ - "1.8b-v2-q3_K_S", - "1.6\u202fGB" - ], - [ - "1.8b-v2-q3_K_M", - "1.7\u202fGB" - ], - [ - "1.8b-v2-q3_K_L", - "1.7\u202fGB" - ], - [ - "1.8b-v2-q4_0", - "1.7\u202fGB" - ], - [ - "1.8b-v2-q4_1", - "1.8\u202fGB" - ], - [ - "1.8b-v2-q4_K_S", - "1.7\u202fGB" - ], - [ - "1.8b-v2-q4_K_M", - "1.8\u202fGB" - ], - [ - "1.8b-v2-q5_0", - "1.9\u202fGB" - ], - [ - "1.8b-v2-q5_1", - "2.0\u202fGB" - ], - [ - "1.8b-v2-q5_K_S", - "1.9\u202fGB" - ], - [ - "1.8b-v2-q5_K_M", - "2.0\u202fGB" - ], - [ - "1.8b-v2-q6_K", - "2.1\u202fGB" - ], - [ - "1.8b-v2-q8_0", - "2.4\u202fGB" - ] - ], - "image": true, - "author": "Vikhyatk" - }, "smollm": { "url": "https://ollama.com/library/smollm", "description": "\ud83e\ude90 A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset.", @@ -18183,674 +18527,866 @@ "image": false, "author": "HuggingFaceTB" }, - "stable-beluga": { - "url": "https://ollama.com/library/stable-beluga", - "description": "\ud83e\ude90 A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset.", + "starling-lm": { + "url": "https://ollama.com/library/starling-lm", + "description": "Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.", "tags": [ [ "latest", - "991\u202fMB" - ], - [ - "135m", - "92\u202fMB" - ], - [ - "360m", - "229\u202fMB" - ], - [ - "1.7b", - "991\u202fMB" - ], - [ - "135m-base-v0.2-fp16", - "271\u202fMB" - ], - [ - "135m-base-v0.2-q2_K", - "88\u202fMB" - ], - [ - "135m-base-v0.2-q3_K_S", - "88\u202fMB" - ], - [ - "135m-base-v0.2-q3_K_M", - "94\u202fMB" - ], - [ - "135m-base-v0.2-q3_K_L", - "98\u202fMB" - ], - [ - "135m-base-v0.2-q4_0", - "92\u202fMB" - ], - [ - "135m-base-v0.2-q4_1", - "98\u202fMB" - ], - [ - "135m-base-v0.2-q4_K_S", - "102\u202fMB" - ], - [ - "135m-base-v0.2-q4_K_M", - "105\u202fMB" - ], - [ - "135m-base-v0.2-q5_0", - "105\u202fMB" - ], - [ - "135m-base-v0.2-q5_1", - "112\u202fMB" - ], - [ - "135m-base-v0.2-q5_K_S", - "110\u202fMB" - ], - [ - "135m-base-v0.2-q5_K_M", - "112\u202fMB" - ], - [ - "135m-base-v0.2-q6_K", - "138\u202fMB" - ], - [ - "135m-base-v0.2-q8_0", - "145\u202fMB" - ], - [ - "135m-instruct-v0.2-fp16", - "271\u202fMB" - ], - [ - "135m-instruct-v0.2-q2_K", - "88\u202fMB" - ], - [ - "135m-instruct-v0.2-q3_K_S", - "88\u202fMB" - ], - [ - "135m-instruct-v0.2-q3_K_M", - "94\u202fMB" - ], - [ - "135m-instruct-v0.2-q3_K_L", - "98\u202fMB" - ], - [ - "135m-instruct-v0.2-q4_0", - "92\u202fMB" - ], - [ - "135m-instruct-v0.2-q4_1", - "98\u202fMB" - ], - [ - "135m-instruct-v0.2-q4_K_S", - "102\u202fMB" - ], - [ - "135m-instruct-v0.2-q4_K_M", - "105\u202fMB" - ], - [ - "135m-instruct-v0.2-q5_0", - "105\u202fMB" - ], - [ - "135m-instruct-v0.2-q5_1", - "112\u202fMB" - ], - [ - "135m-instruct-v0.2-q5_K_S", - "110\u202fMB" - ], - [ - "135m-instruct-v0.2-q5_K_M", - "112\u202fMB" - ], - [ - "135m-instruct-v0.2-q6_K", - "138\u202fMB" - ], - [ - "135m-instruct-v0.2-q8_0", - "145\u202fMB" - ], - [ - "360m-base-v0.2-fp16", - "726\u202fMB" - ], - [ - "360m-base-v0.2-q2_K", - "219\u202fMB" - ], - [ - "360m-base-v0.2-q3_K_S", - "219\u202fMB" - ], - [ - "360m-base-v0.2-q3_K_M", - "235\u202fMB" - ], - [ - "360m-base-v0.2-q3_K_L", - "246\u202fMB" - ], - [ - "360m-base-v0.2-q4_0", - "229\u202fMB" - ], - [ - "360m-base-v0.2-q4_1", - "249\u202fMB" - ], - [ - "360m-base-v0.2-q4_K_S", - "260\u202fMB" - ], - [ - "360m-base-v0.2-q4_K_M", - "271\u202fMB" - ], - [ - "360m-base-v0.2-q5_0", - "268\u202fMB" - ], - [ - "360m-base-v0.2-q5_1", - "288\u202fMB" - ], - [ - "360m-base-v0.2-q5_K_S", - "283\u202fMB" - ], - [ - "360m-base-v0.2-q5_K_M", - "290\u202fMB" - ], - [ - "360m-base-v0.2-q6_K", - "367\u202fMB" - ], - [ - "360m-base-v0.2-q8_0", - "386\u202fMB" - ], - [ - "360m-instruct-v0.2-fp16", - "726\u202fMB" - ], - [ - "360m-instruct-v0.2-q2_K", - "219\u202fMB" - ], - [ - "360m-instruct-v0.2-q3_K_S", - "219\u202fMB" - ], - [ - "360m-instruct-v0.2-q3_K_M", - "235\u202fMB" - ], - [ - "360m-instruct-v0.2-q3_K_L", - "246\u202fMB" - ], - [ - "360m-instruct-v0.2-q4_0", - "229\u202fMB" - ], - [ - "360m-instruct-v0.2-q4_1", - "249\u202fMB" - ], - [ - "360m-instruct-v0.2-q4_K_S", - "260\u202fMB" - ], - [ - "360m-instruct-v0.2-q4_K_M", - "271\u202fMB" - ], - [ - "360m-instruct-v0.2-q5_0", - "268\u202fMB" - ], - [ - "360m-instruct-v0.2-q5_1", - "288\u202fMB" - ], - [ - "360m-instruct-v0.2-q5_K_S", - "283\u202fMB" - ], - [ - "360m-instruct-v0.2-q5_K_M", - "290\u202fMB" - ], - [ - "360m-instruct-v0.2-q6_K", - "367\u202fMB" - ], - [ - "360m-instruct-v0.2-q8_0", - "386\u202fMB" - ], - [ - "1.7b-base-v0.2-fp16", - "3.4\u202fGB" - ], - [ - "1.7b-base-v0.2-q2_K", - "675\u202fMB" - ], - [ - "1.7b-base-v0.2-q3_K_S", - "777\u202fMB" - ], - [ - "1.7b-base-v0.2-q3_K_M", - "860\u202fMB" - ], - [ - "1.7b-base-v0.2-q3_K_L", - "933\u202fMB" - ], - [ - "1.7b-base-v0.2-q4_0", - "991\u202fMB" - ], - [ - "1.7b-base-v0.2-q4_1", - "1.1\u202fGB" - ], - [ - "1.7b-base-v0.2-q4_K_S", - "999\u202fMB" - ], - [ - "1.7b-base-v0.2-q4_K_M", - "1.1\u202fGB" - ], - [ - "1.7b-base-v0.2-q5_0", - "1.2\u202fGB" - ], - [ - "1.7b-base-v0.2-q5_1", - "1.3\u202fGB" - ], - [ - "1.7b-base-v0.2-q5_K_S", - "1.2\u202fGB" - ], - [ - "1.7b-base-v0.2-q5_K_M", - "1.2\u202fGB" - ], - [ - "1.7b-base-v0.2-q6_K", - "1.4\u202fGB" - ], - [ - "1.7b-base-v0.2-q8_0", - "1.8\u202fGB" - ], - [ - "1.7b-instruct-v0.2-fp16", - "3.4\u202fGB" - ], - [ - "1.7b-instruct-v0.2-q2_K", - "675\u202fMB" - ], - [ - "1.7b-instruct-v0.2-q3_K_S", - "777\u202fMB" - ], - [ - "1.7b-instruct-v0.2-q3_K_M", - "860\u202fMB" - ], - [ - "1.7b-instruct-v0.2-q3_K_L", - "933\u202fMB" - ], - [ - "1.7b-instruct-v0.2-q4_0", - "991\u202fMB" - ], - [ - "1.7b-instruct-v0.2-q4_1", - "1.1\u202fGB" - ], - [ - "1.7b-instruct-v0.2-q4_K_S", - "999\u202fMB" - ], - [ - "1.7b-instruct-v0.2-q4_K_M", - "1.1\u202fGB" - ], - [ - "1.7b-instruct-v0.2-q5_0", - "1.2\u202fGB" - ], - [ - "1.7b-instruct-v0.2-q5_1", - "1.3\u202fGB" - ], - [ - "1.7b-instruct-v0.2-q5_K_S", - "1.2\u202fGB" - ], - [ - "1.7b-instruct-v0.2-q5_K_M", - "1.2\u202fGB" - ], - [ - "1.7b-instruct-v0.2-q6_K", - "1.4\u202fGB" - ], - [ - "1.7b-instruct-v0.2-q8_0", - "1.8\u202fGB" - ] - ], - "image": false, - "author": "Stability AI" - }, - "qwen2-math": { - "url": "https://ollama.com/library/qwen2-math", - "description": "Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o).", - "tags": [ - [ - "latest", - "4.4\u202fGB" - ], - [ - "1.5b", - "935\u202fMB" - ], - [ - "7b", - "4.4\u202fGB" - ], - [ - "72b", - "41\u202fGB" - ], - [ - "1.5b-instruct", - "935\u202fMB" - ], - [ - "7b-instruct", - "4.4\u202fGB" - ], - [ - "72b-instruct", - "41\u202fGB" - ], - [ - "1.5b-instruct-fp16", - "3.1\u202fGB" - ], - [ - "1.5b-instruct-q2_K", - "676\u202fMB" - ], - [ - "1.5b-instruct-q3_K_S", - "761\u202fMB" - ], - [ - "1.5b-instruct-q3_K_M", - "824\u202fMB" - ], - [ - "1.5b-instruct-q3_K_L", - "880\u202fMB" - ], - [ - "1.5b-instruct-q4_0", - "935\u202fMB" - ], - [ - "1.5b-instruct-q4_1", - "1.0\u202fGB" - ], - [ - "1.5b-instruct-q4_K_S", - "940\u202fMB" - ], - [ - "1.5b-instruct-q4_K_M", - "986\u202fMB" - ], - [ - "1.5b-instruct-q5_0", - "1.1\u202fGB" - ], - [ - "1.5b-instruct-q5_1", - "1.2\u202fGB" - ], - [ - "1.5b-instruct-q5_K_S", - "1.1\u202fGB" - ], - [ - "1.5b-instruct-q5_K_M", - "1.1\u202fGB" - ], - [ - "1.5b-instruct-q6_K", - "1.3\u202fGB" - ], - [ - "1.5b-instruct-q8_0", - "1.6\u202fGB" - ], - [ - "7b-instruct-fp16", - "15\u202fGB" - ], - [ - "7b-instruct-q2_K", - "3.0\u202fGB" - ], - [ - "7b-instruct-q3_K_S", - "3.5\u202fGB" - ], - [ - "7b-instruct-q3_K_M", - "3.8\u202fGB" - ], - [ - "7b-instruct-q3_K_L", "4.1\u202fGB" ], [ - "7b-instruct-q4_0", + "7b", + "4.1\u202fGB" + ], + [ + "alpha", + "4.1\u202fGB" + ], + [ + "beta", + "4.1\u202fGB" + ], + [ + "7b-alpha", + "4.1\u202fGB" + ], + [ + "7b-beta", + "4.1\u202fGB" + ], + [ + "7b-alpha-fp16", + "14\u202fGB" + ], + [ + "7b-alpha-q2_K", + "2.7\u202fGB" + ], + [ + "7b-alpha-q3_K_S", + "3.2\u202fGB" + ], + [ + "7b-alpha-q3_K_M", + "3.5\u202fGB" + ], + [ + "7b-alpha-q3_K_L", + "3.8\u202fGB" + ], + [ + "7b-alpha-q4_0", + "4.1\u202fGB" + ], + [ + "7b-alpha-q4_1", + "4.6\u202fGB" + ], + [ + "7b-alpha-q4_K_S", + "4.1\u202fGB" + ], + [ + "7b-alpha-q4_K_M", "4.4\u202fGB" ], [ - "7b-instruct-q4_1", - "4.9\u202fGB" + "7b-alpha-q5_0", + "5.0\u202fGB" ], [ - "7b-instruct-q4_K_S", - "4.5\u202fGB" - ], - [ - "7b-instruct-q4_K_M", - "4.7\u202fGB" - ], - [ - "7b-instruct-q5_0", - "5.3\u202fGB" - ], - [ - "7b-instruct-q5_1", - "5.8\u202fGB" - ], - [ - "7b-instruct-q5_K_S", - "5.3\u202fGB" - ], - [ - "7b-instruct-q5_K_M", + "7b-alpha-q5_1", "5.4\u202fGB" ], [ - "7b-instruct-q6_K", - "6.3\u202fGB" + "7b-alpha-q5_K_S", + "5.0\u202fGB" ], [ - "7b-instruct-q8_0", - "8.1\u202fGB" + "7b-alpha-q5_K_M", + "5.1\u202fGB" ], [ - "72b-instruct-fp16", - "145\u202fGB" + "7b-alpha-q6_K", + "5.9\u202fGB" ], [ - "72b-instruct-q2_K", - "30\u202fGB" + "7b-alpha-q8_0", + "7.7\u202fGB" ], [ - "72b-instruct-q3_K_S", - "34\u202fGB" + "7b-beta-fp16", + "14\u202fGB" ], [ - "72b-instruct-q3_K_M", - "38\u202fGB" + "7b-beta-q2_K", + "2.7\u202fGB" ], [ - "72b-instruct-q3_K_L", - "40\u202fGB" + "7b-beta-q3_K_S", + "3.2\u202fGB" ], [ - "72b-instruct-q4_0", - "41\u202fGB" + "7b-beta-q3_K_M", + "3.5\u202fGB" ], [ - "72b-instruct-q4_1", - "46\u202fGB" + "7b-beta-q3_K_L", + "3.8\u202fGB" ], [ - "72b-instruct-q4_K_S", - "44\u202fGB" + "7b-beta-q4_0", + "4.1\u202fGB" ], [ - "72b-instruct-q4_K_M", - "47\u202fGB" + "7b-beta-q4_1", + "4.6\u202fGB" ], [ - "72b-instruct-q5_0", - "50\u202fGB" + "7b-beta-q4_K_S", + "4.1\u202fGB" ], [ - "72b-instruct-q5_1", - "55\u202fGB" + "7b-beta-q4_K_M", + "4.4\u202fGB" ], [ - "72b-instruct-q5_K_S", - "51\u202fGB" + "7b-beta-q5_0", + "5.0\u202fGB" ], [ - "72b-instruct-q5_K_M", - "54\u202fGB" + "7b-beta-q5_1", + "5.4\u202fGB" ], [ - "72b-instruct-q6_K", - "64\u202fGB" + "7b-beta-q5_K_S", + "5.0\u202fGB" ], [ - "72b-instruct-q8_0", - "77\u202fGB" + "7b-beta-q5_K_M", + "5.1\u202fGB" + ], + [ + "7b-beta-q6_K", + "5.9\u202fGB" + ], + [ + "7b-beta-q8_0", + "7.7\u202fGB" ] ], "image": false, - "author": "Alibaba" + "author": "Berkeley Nest" }, - "dolphin-phi": { - "url": "https://ollama.com/library/dolphin-phi", - "description": "2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.", + "reflection": { + "url": "https://ollama.com/library/reflection", + "description": "A high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct course.", "tags": [ [ "latest", - "1.6\u202fGB" + "40\u202fGB" ], [ - "2.7b", - "1.6\u202fGB" + "70b", + "40\u202fGB" ], [ - "2.7b-v2.6", - "1.6\u202fGB" + "70b-fp16", + "141\u202fGB" ], [ - "2.7b-v2.6-q2_K", - "1.2\u202fGB" + "70b-q2_K", + "26\u202fGB" ], [ - "2.7b-v2.6-q3_K_S", - "1.3\u202fGB" + "70b-q3_K_S", + "31\u202fGB" ], [ - "2.7b-v2.6-q3_K_M", + "70b-q3_K_M", + "34\u202fGB" + ], + [ + "70b-q3_K_L", + "37\u202fGB" + ], + [ + "70b-q4_0", + "40\u202fGB" + ], + [ + "70b-q4_1", + "44\u202fGB" + ], + [ + "70b-q4_K_S", + "40\u202fGB" + ], + [ + "70b-q4_K_M", + "43\u202fGB" + ], + [ + "70b-q5_0", + "49\u202fGB" + ], + [ + "70b-q5_1", + "53\u202fGB" + ], + [ + "70b-q5_K_S", + "49\u202fGB" + ], + [ + "70b-q5_K_M", + "50\u202fGB" + ], + [ + "70b-q6_K", + "58\u202fGB" + ], + [ + "70b-q8_0", + "75\u202fGB" + ] + ], + "image": false, + "author": "Mattshumer" + }, + "moondream": { + "url": "https://ollama.com/library/moondream", + "description": "moondream2 is a small vision language model designed to run efficiently on edge devices.", + "tags": [ + [ + "latest", + "1.7\u202fGB" + ], + [ + "1.8b", + "1.7\u202fGB" + ], + [ + "v2", + "1.7\u202fGB" + ], + [ + "1.8b-v2-fp16", + "3.7\u202fGB" + ], + [ + "1.8b-v2-q2_K", "1.5\u202fGB" ], [ - "2.7b-v2.6-q3_K_L", + "1.8b-v2-q3_K_S", "1.6\u202fGB" ], [ - "2.7b-v2.6-q4_0", - "1.6\u202fGB" + "1.8b-v2-q3_K_M", + "1.7\u202fGB" ], [ - "2.7b-v2.6-q4_K_S", - "1.6\u202fGB" + "1.8b-v2-q3_K_L", + "1.7\u202fGB" ], [ - "2.7b-v2.6-q4_K_M", + "1.8b-v2-q4_0", + "1.7\u202fGB" + ], + [ + "1.8b-v2-q4_1", "1.8\u202fGB" ], [ - "2.7b-v2.6-q5_0", + "1.8b-v2-q4_K_S", + "1.7\u202fGB" + ], + [ + "1.8b-v2-q4_K_M", + "1.8\u202fGB" + ], + [ + "1.8b-v2-q5_0", "1.9\u202fGB" ], [ - "2.7b-v2.6-q5_K_S", + "1.8b-v2-q5_1", + "2.0\u202fGB" + ], + [ + "1.8b-v2-q5_K_S", "1.9\u202fGB" ], [ - "2.7b-v2.6-q5_K_M", + "1.8b-v2-q5_K_M", + "2.0\u202fGB" + ], + [ + "1.8b-v2-q6_K", "2.1\u202fGB" ], [ - "2.7b-v2.6-q6_K", - "2.3\u202fGB" + "1.8b-v2-q8_0", + "2.4\u202fGB" + ] + ], + "image": true, + "author": "Vikhyatk" + }, + "snowflake-arctic-embed": { + "url": "https://ollama.com/library/snowflake-arctic-embed", + "description": "A suite of text embedding models by Snowflake, optimized for performance.", + "tags": [ + [ + "latest", + "669\u202fMB" ], [ - "2.7b-v2.6-q8_0", - "3.0\u202fGB" + "22m", + "46\u202fMB" + ], + [ + "33m", + "67\u202fMB" + ], + [ + "110m", + "219\u202fMB" + ], + [ + "137m", + "274\u202fMB" + ], + [ + "335m", + "669\u202fMB" + ], + [ + "l", + "669\u202fMB" + ], + [ + "m", + "219\u202fMB" + ], + [ + "m-long", + "274\u202fMB" + ], + [ + "s", + "67\u202fMB" + ], + [ + "xs", + "46\u202fMB" + ], + [ + "22m-xs-fp16", + "46\u202fMB" + ], + [ + "33m-s-fp16", + "67\u202fMB" + ], + [ + "110m-m-fp16", + "219\u202fMB" + ], + [ + "137m-m-long-fp16", + "274\u202fMB" + ], + [ + "335m-l-fp16", + "669\u202fMB" + ] + ], + "image": false, + "author": "Snowflake" + }, + "samantha-mistral": { + "url": "https://ollama.com/library/samantha-mistral", + "description": "A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.", + "tags": [ + [ + "latest", + "4.1\u202fGB" + ], + [ + "7b", + "4.1\u202fGB" + ], + [ + "7b-text", + "4.1\u202fGB" + ], + [ + "7b-v1.2-text", + "4.1\u202fGB" + ], + [ + "7b-instruct-fp16", + "14\u202fGB" + ], + [ + "7b-instruct-q2_K", + "3.1\u202fGB" + ], + [ + "7b-instruct-q3_K_S", + "3.2\u202fGB" + ], + [ + "7b-instruct-q3_K_M", + "3.5\u202fGB" + ], + [ + "7b-instruct-q3_K_L", + "3.8\u202fGB" + ], + [ + "7b-instruct-q4_0", + "4.1\u202fGB" + ], + [ + "7b-instruct-q4_1", + "4.6\u202fGB" + ], + [ + "7b-instruct-q4_K_S", + "4.1\u202fGB" + ], + [ + "7b-instruct-q4_K_M", + "4.4\u202fGB" + ], + [ + "7b-instruct-q5_0", + "5.0\u202fGB" + ], + [ + "7b-instruct-q5_1", + "5.4\u202fGB" + ], + [ + "7b-instruct-q5_K_S", + "5.0\u202fGB" + ], + [ + "7b-instruct-q5_K_M", + "5.1\u202fGB" + ], + [ + "7b-instruct-q6_K", + "5.9\u202fGB" + ], + [ + "7b-instruct-q8_0", + "7.7\u202fGB" + ], + [ + "7b-text-fp16", + "14\u202fGB" + ], + [ + "7b-text-q2_K", + "3.1\u202fGB" + ], + [ + "7b-text-q3_K_S", + "3.2\u202fGB" + ], + [ + "7b-text-q3_K_M", + "3.5\u202fGB" + ], + [ + "7b-text-q3_K_L", + "3.8\u202fGB" + ], + [ + "7b-text-q4_0", + "4.1\u202fGB" + ], + [ + "7b-text-q4_1", + "4.6\u202fGB" + ], + [ + "7b-text-q4_K_S", + "4.1\u202fGB" + ], + [ + "7b-text-q4_K_M", + "4.4\u202fGB" + ], + [ + "7b-text-q5_0", + "5.0\u202fGB" + ], + [ + "7b-text-q5_1", + "5.4\u202fGB" + ], + [ + "7b-text-q5_K_S", + "5.0\u202fGB" + ], + [ + "7b-text-q5_K_M", + "5.1\u202fGB" + ], + [ + "7b-text-q6_K", + "5.9\u202fGB" + ], + [ + "7b-text-q8_0", + "7.7\u202fGB" + ], + [ + "7b-v1.2-text-fp16", + "14\u202fGB" + ], + [ + "7b-v1.2-text-q2_K", + "3.1\u202fGB" + ], + [ + "7b-v1.2-text-q3_K_S", + "3.2\u202fGB" + ], + [ + "7b-v1.2-text-q3_K_M", + "3.5\u202fGB" + ], + [ + "7b-v1.2-text-q3_K_L", + "3.8\u202fGB" + ], + [ + "7b-v1.2-text-q4_0", + "4.1\u202fGB" + ], + [ + "7b-v1.2-text-q4_1", + "4.6\u202fGB" + ], + [ + "7b-v1.2-text-q4_K_S", + "4.1\u202fGB" + ], + [ + "7b-v1.2-text-q4_K_M", + "4.4\u202fGB" + ], + [ + "7b-v1.2-text-q5_0", + "5.0\u202fGB" + ], + [ + "7b-v1.2-text-q5_1", + "5.4\u202fGB" + ], + [ + "7b-v1.2-text-q5_K_S", + "5.0\u202fGB" + ], + [ + "7b-v1.2-text-q5_K_M", + "5.1\u202fGB" + ], + [ + "7b-v1.2-text-q6_K", + "5.9\u202fGB" + ], + [ + "7b-v1.2-text-q8_0", + "7.7\u202fGB" ] ], "image": false, "author": "Eric Hartford" }, + "solar": { + "url": "https://ollama.com/library/solar", + "description": "A compact, yet powerful 10.7B large language model designed for single-turn conversation.", + "tags": [ + [ + "latest", + "6.1\u202fGB" + ], + [ + "10.7b", + "6.1\u202fGB" + ], + [ + "10.7b-instruct-v1-fp16", + "21\u202fGB" + ], + [ + "10.7b-instruct-v1-q2_K", + "4.5\u202fGB" + ], + [ + "10.7b-instruct-v1-q3_K_S", + "4.7\u202fGB" + ], + [ + "10.7b-instruct-v1-q3_K_M", + "5.2\u202fGB" + ], + [ + "10.7b-instruct-v1-q3_K_L", + "5.7\u202fGB" + ], + [ + "10.7b-instruct-v1-q4_0", + "6.1\u202fGB" + ], + [ + "10.7b-instruct-v1-q4_1", + "6.7\u202fGB" + ], + [ + "10.7b-instruct-v1-q4_K_S", + "6.1\u202fGB" + ], + [ + "10.7b-instruct-v1-q4_K_M", + "6.5\u202fGB" + ], + [ + "10.7b-instruct-v1-q5_0", + "7.4\u202fGB" + ], + [ + "10.7b-instruct-v1-q5_1", + "8.1\u202fGB" + ], + [ + "10.7b-instruct-v1-q5_K_S", + "7.4\u202fGB" + ], + [ + "10.7b-instruct-v1-q5_K_M", + "7.6\u202fGB" + ], + [ + "10.7b-instruct-v1-q6_K", + "8.8\u202fGB" + ], + [ + "10.7b-instruct-v1-q8_0", + "11\u202fGB" + ], + [ + "10.7b-text-v1-fp16", + "21\u202fGB" + ], + [ + "10.7b-text-v1-q2_K", + "4.5\u202fGB" + ], + [ + "10.7b-text-v1-q3_K_S", + "4.7\u202fGB" + ], + [ + "10.7b-text-v1-q3_K_M", + "5.2\u202fGB" + ], + [ + "10.7b-text-v1-q3_K_L", + "5.7\u202fGB" + ], + [ + "10.7b-text-v1-q4_0", + "6.1\u202fGB" + ], + [ + "10.7b-text-v1-q4_1", + "6.7\u202fGB" + ], + [ + "10.7b-text-v1-q4_K_S", + "6.1\u202fGB" + ], + [ + "10.7b-text-v1-q4_K_M", + "6.5\u202fGB" + ], + [ + "10.7b-text-v1-q5_0", + "7.4\u202fGB" + ], + [ + "10.7b-text-v1-q5_1", + "8.1\u202fGB" + ], + [ + "10.7b-text-v1-q5_K_S", + "7.4\u202fGB" + ], + [ + "10.7b-text-v1-q5_K_M", + "7.6\u202fGB" + ], + [ + "10.7b-text-v1-q6_K", + "8.8\u202fGB" + ], + [ + "10.7b-text-v1-q8_0", + "11\u202fGB" + ] + ], + "image": false, + "author": "Upstage" + }, + "orca2": { + "url": "https://ollama.com/library/orca2", + "description": "Orca 2 is built by Microsoft research, and are a fine-tuned version of Meta's Llama 2 models. The model is designed to excel particularly in reasoning.", + "tags": [ + [ + "latest", + "3.8\u202fGB" + ], + [ + "7b", + "3.8\u202fGB" + ], + [ + "13b", + "7.4\u202fGB" + ], + [ + "7b-fp16", + "13\u202fGB" + ], + [ + "7b-q2_K", + "2.8\u202fGB" + ], + [ + "7b-q3_K_S", + "2.9\u202fGB" + ], + [ + "7b-q3_K_M", + "3.3\u202fGB" + ], + [ + "7b-q3_K_L", + "3.6\u202fGB" + ], + [ + "7b-q4_0", + "3.8\u202fGB" + ], + [ + "7b-q4_1", + "4.2\u202fGB" + ], + [ + "7b-q4_K_S", + "3.9\u202fGB" + ], + [ + "7b-q4_K_M", + "4.1\u202fGB" + ], + [ + "7b-q5_0", + "4.7\u202fGB" + ], + [ + "7b-q5_1", + "5.1\u202fGB" + ], + [ + "7b-q5_K_S", + "4.7\u202fGB" + ], + [ + "7b-q5_K_M", + "4.8\u202fGB" + ], + [ + "7b-q6_K", + "5.5\u202fGB" + ], + [ + "7b-q8_0", + "7.2\u202fGB" + ], + [ + "13b-fp16", + "26\u202fGB" + ], + [ + "13b-q2_K", + "5.4\u202fGB" + ], + [ + "13b-q3_K_S", + "5.7\u202fGB" + ], + [ + "13b-q3_K_M", + "6.3\u202fGB" + ], + [ + "13b-q3_K_L", + "6.9\u202fGB" + ], + [ + "13b-q4_0", + "7.4\u202fGB" + ], + [ + "13b-q4_1", + "8.2\u202fGB" + ], + [ + "13b-q4_K_S", + "7.4\u202fGB" + ], + [ + "13b-q4_K_M", + "7.9\u202fGB" + ], + [ + "13b-q5_0", + "9.0\u202fGB" + ], + [ + "13b-q5_1", + "9.8\u202fGB" + ], + [ + "13b-q5_K_S", + "9.0\u202fGB" + ], + [ + "13b-q5_K_M", + "9.2\u202fGB" + ], + [ + "13b-q6_K", + "11\u202fGB" + ], + [ + "13b-q8_0", + "14\u202fGB" + ] + ], + "image": false, + "author": "Microsoft Research" + }, "deepseek-v2": { "url": "https://ollama.com/library/deepseek-v2", "description": "A strong, economical, and efficient Mixture-of-Experts language model.", @@ -18871,14 +19407,6 @@ "lite", "8.9\u202fGB" ], - [ - "16b-lite-chat-f16", - "31\u202fGB" - ], - [ - "236b-chat-f16", - "472\u202fGB" - ], [ "16b-lite-chat-fp16", "31\u202fGB" @@ -19003,81 +19531,209 @@ "image": false, "author": "DeepSeek Team" }, - "bakllava": { - "url": "https://ollama.com/library/bakllava", - "description": "BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.", + "stable-beluga": { + "url": "https://ollama.com/library/stable-beluga", + "description": "Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.", "tags": [ [ "latest", - "4.7\u202fGB" - ], - [ - "7b", - "4.7\u202fGB" - ], - [ - "7b-v1-fp16", - "15\u202fGB" - ], - [ - "7b-v1-q2_K", - "3.7\u202fGB" - ], - [ - "7b-v1-q3_K_S", "3.8\u202fGB" ], [ - "7b-v1-q3_K_M", + "7b", + "3.8\u202fGB" + ], + [ + "13b", + "7.4\u202fGB" + ], + [ + "70b", + "39\u202fGB" + ], + [ + "7b-fp16", + "13\u202fGB" + ], + [ + "7b-q2_K", + "2.8\u202fGB" + ], + [ + "7b-q3_K_S", + "2.9\u202fGB" + ], + [ + "7b-q3_K_M", + "3.3\u202fGB" + ], + [ + "7b-q3_K_L", + "3.6\u202fGB" + ], + [ + "7b-q4_0", + "3.8\u202fGB" + ], + [ + "7b-q4_1", + "4.2\u202fGB" + ], + [ + "7b-q4_K_S", + "3.9\u202fGB" + ], + [ + "7b-q4_K_M", "4.1\u202fGB" ], [ - "7b-v1-q3_K_L", - "4.4\u202fGB" - ], - [ - "7b-v1-q4_0", + "7b-q5_0", "4.7\u202fGB" ], [ - "7b-v1-q4_1", - "5.2\u202fGB" + "7b-q5_1", + "5.1\u202fGB" ], [ - "7b-v1-q4_K_S", + "7b-q5_K_S", + "4.7\u202fGB" + ], + [ + "7b-q5_K_M", "4.8\u202fGB" ], [ - "7b-v1-q4_K_M", - "5.0\u202fGB" + "7b-q6_K", + "5.5\u202fGB" ], [ - "7b-v1-q5_0", - "5.6\u202fGB" + "7b-q8_0", + "7.2\u202fGB" ], [ - "7b-v1-q5_1", - "6.1\u202fGB" + "13b-fp16", + "26\u202fGB" ], [ - "7b-v1-q5_K_S", - "5.6\u202fGB" + "13b-q2_K", + "5.4\u202fGB" ], [ - "7b-v1-q5_K_M", - "5.8\u202fGB" + "13b-q3_K_S", + "5.7\u202fGB" ], [ - "7b-v1-q6_K", - "6.6\u202fGB" + "13b-q3_K_M", + "6.3\u202fGB" ], [ - "7b-v1-q8_0", - "8.3\u202fGB" + "13b-q3_K_L", + "6.9\u202fGB" + ], + [ + "13b-q4_0", + "7.4\u202fGB" + ], + [ + "13b-q4_1", + "8.2\u202fGB" + ], + [ + "13b-q4_K_S", + "7.4\u202fGB" + ], + [ + "13b-q4_K_M", + "7.9\u202fGB" + ], + [ + "13b-q5_0", + "9.0\u202fGB" + ], + [ + "13b-q5_1", + "9.8\u202fGB" + ], + [ + "13b-q5_K_S", + "9.0\u202fGB" + ], + [ + "13b-q5_K_M", + "9.2\u202fGB" + ], + [ + "13b-q6_K", + "11\u202fGB" + ], + [ + "13b-q8_0", + "14\u202fGB" + ], + [ + "70b-fp16", + "138\u202fGB" + ], + [ + "70b-q2_K", + "29\u202fGB" + ], + [ + "70b-q3_K_S", + "30\u202fGB" + ], + [ + "70b-q3_K_M", + "33\u202fGB" + ], + [ + "70b-q3_K_L", + "36\u202fGB" + ], + [ + "70b-q4_0", + "39\u202fGB" + ], + [ + "70b-q4_1", + "43\u202fGB" + ], + [ + "70b-q4_K_S", + "39\u202fGB" + ], + [ + "70b-q4_K_M", + "41\u202fGB" + ], + [ + "70b-q5_0", + "47\u202fGB" + ], + [ + "70b-q5_1", + "52\u202fGB" + ], + [ + "70b-q5_K_S", + "47\u202fGB" + ], + [ + "70b-q5_K_M", + "49\u202fGB" + ], + [ + "70b-q6_K", + "57\u202fGB" + ], + [ + "70b-q8_0", + "73\u202fGB" ] ], - "image": true, - "author": "Skunkworks AI" + "image": false, + "author": "Stability AI" }, "glm4": { "url": "https://ollama.com/library/glm4", @@ -19215,6 +19871,74 @@ "image": false, "author": "THUDM" }, + "dolphin-phi": { + "url": "https://ollama.com/library/dolphin-phi", + "description": "2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.", + "tags": [ + [ + "latest", + "1.6\u202fGB" + ], + [ + "2.7b", + "1.6\u202fGB" + ], + [ + "2.7b-v2.6", + "1.6\u202fGB" + ], + [ + "2.7b-v2.6-q2_K", + "1.2\u202fGB" + ], + [ + "2.7b-v2.6-q3_K_S", + "1.3\u202fGB" + ], + [ + "2.7b-v2.6-q3_K_M", + "1.5\u202fGB" + ], + [ + "2.7b-v2.6-q3_K_L", + "1.6\u202fGB" + ], + [ + "2.7b-v2.6-q4_0", + "1.6\u202fGB" + ], + [ + "2.7b-v2.6-q4_K_S", + "1.6\u202fGB" + ], + [ + "2.7b-v2.6-q4_K_M", + "1.8\u202fGB" + ], + [ + "2.7b-v2.6-q5_0", + "1.9\u202fGB" + ], + [ + "2.7b-v2.6-q5_K_S", + "1.9\u202fGB" + ], + [ + "2.7b-v2.6-q5_K_M", + "2.1\u202fGB" + ], + [ + "2.7b-v2.6-q6_K", + "2.3\u202fGB" + ], + [ + "2.7b-v2.6-q8_0", + "3.0\u202fGB" + ] + ], + "image": false, + "author": "Eric Hartford" + }, "wizardlm-uncensored": { "url": "https://ollama.com/library/wizardlm-uncensored", "description": "Uncensored version of Wizard LM model", @@ -19295,438 +20019,6 @@ "image": false, "author": "TheBloke AI" }, - "yarn-mistral": { - "url": "https://ollama.com/library/yarn-mistral", - "description": "An extension of Mistral to support context windows of 64K or 128K.", - "tags": [ - [ - "latest", - "4.1\u202fGB" - ], - [ - "7b", - "4.1\u202fGB" - ], - [ - "7b-128k", - "4.1\u202fGB" - ], - [ - "7b-64k", - "4.1\u202fGB" - ], - [ - "7b-128k-fp16", - "14\u202fGB" - ], - [ - "7b-128k-q2_K", - "3.1\u202fGB" - ], - [ - "7b-128k-q3_K_S", - "3.2\u202fGB" - ], - [ - "7b-128k-q3_K_M", - "3.5\u202fGB" - ], - [ - "7b-128k-q3_K_L", - "3.8\u202fGB" - ], - [ - "7b-128k-q4_0", - "4.1\u202fGB" - ], - [ - "7b-128k-q4_1", - "4.6\u202fGB" - ], - [ - "7b-128k-q4_K_S", - "4.1\u202fGB" - ], - [ - "7b-128k-q4_K_M", - "4.4\u202fGB" - ], - [ - "7b-128k-q5_0", - "5.0\u202fGB" - ], - [ - "7b-128k-q5_1", - "5.4\u202fGB" - ], - [ - "7b-128k-q5_K_S", - "5.0\u202fGB" - ], - [ - "7b-128k-q5_K_M", - "5.1\u202fGB" - ], - [ - "7b-128k-q6_K", - "5.9\u202fGB" - ], - [ - "7b-128k-q8_0", - "7.7\u202fGB" - ], - [ - "7b-64k-q2_K", - "3.1\u202fGB" - ], - [ - "7b-64k-q3_K_S", - "3.2\u202fGB" - ], - [ - "7b-64k-q3_K_M", - "3.5\u202fGB" - ], - [ - "7b-64k-q3_K_L", - "3.8\u202fGB" - ], - [ - "7b-64k-q4_0", - "4.1\u202fGB" - ], - [ - "7b-64k-q4_1", - "4.6\u202fGB" - ], - [ - "7b-64k-q4_K_S", - "4.1\u202fGB" - ], - [ - "7b-64k-q4_K_M", - "4.4\u202fGB" - ], - [ - "7b-64k-q5_0", - "5.0\u202fGB" - ], - [ - "7b-64k-q5_1", - "5.4\u202fGB" - ], - [ - "7b-64k-q5_K_S", - "5.0\u202fGB" - ], - [ - "7b-64k-q5_K_M", - "5.1\u202fGB" - ], - [ - "7b-64k-q6_K", - "5.9\u202fGB" - ], - [ - "7b-64k-q8_0", - "7.7\u202fGB" - ] - ], - "image": false, - "author": "Nous Research" - }, - "phi3.5": { - "url": "https://ollama.com/library/phi3.5", - "description": "A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger sized models.", - "tags": [ - [ - "latest", - "2.2\u202fGB" - ], - [ - "3.8b", - "2.2\u202fGB" - ], - [ - "3.8b-mini-instruct-fp16", - "7.6\u202fGB" - ], - [ - "3.8b-mini-instruct-q2_K", - "1.4\u202fGB" - ], - [ - "3.8b-mini-instruct-q3_K_S", - "1.7\u202fGB" - ], - [ - "3.8b-mini-instruct-q3_K_M", - "2.0\u202fGB" - ], - [ - "3.8b-mini-instruct-q3_K_L", - "2.1\u202fGB" - ], - [ - "3.8b-mini-instruct-q4_0", - "2.2\u202fGB" - ], - [ - "3.8b-mini-instruct-q4_1", - "2.4\u202fGB" - ], - [ - "3.8b-mini-instruct-q4_K_S", - "2.2\u202fGB" - ], - [ - "3.8b-mini-instruct-q4_K_M", - "2.4\u202fGB" - ], - [ - "3.8b-mini-instruct-q5_0", - "2.6\u202fGB" - ], - [ - "3.8b-mini-instruct-q5_1", - "2.9\u202fGB" - ], - [ - "3.8b-mini-instruct-q5_K_S", - "2.6\u202fGB" - ], - [ - "3.8b-mini-instruct-q5_K_M", - "2.8\u202fGB" - ], - [ - "3.8b-mini-instruct-q6_K", - "3.1\u202fGB" - ], - [ - "3.8b-mini-instruct-q8_0", - "4.1\u202fGB" - ] - ], - "image": false, - "author": "Microsoft" - }, - "medllama2": { - "url": "https://ollama.com/library/medllama2", - "description": "Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.", - "tags": [ - [ - "latest", - "3.8\u202fGB" - ], - [ - "7b", - "3.8\u202fGB" - ], - [ - "7b-fp16", - "13\u202fGB" - ], - [ - "7b-q2_K", - "2.8\u202fGB" - ], - [ - "7b-q3_K_S", - "2.9\u202fGB" - ], - [ - "7b-q3_K_M", - "3.3\u202fGB" - ], - [ - "7b-q3_K_L", - "3.6\u202fGB" - ], - [ - "7b-q4_0", - "3.8\u202fGB" - ], - [ - "7b-q4_1", - "4.2\u202fGB" - ], - [ - "7b-q4_K_S", - "3.9\u202fGB" - ], - [ - "7b-q4_K_M", - "4.1\u202fGB" - ], - [ - "7b-q5_0", - "4.7\u202fGB" - ], - [ - "7b-q5_1", - "5.1\u202fGB" - ], - [ - "7b-q5_K_S", - "4.7\u202fGB" - ], - [ - "7b-q5_K_M", - "4.8\u202fGB" - ], - [ - "7b-q6_K", - "5.5\u202fGB" - ], - [ - "7b-q8_0", - "7.2\u202fGB" - ] - ], - "image": false, - "author": "Siraj Raval" - }, - "llama-pro": { - "url": "https://ollama.com/library/llama-pro", - "description": "An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.", - "tags": [ - [ - "latest", - "4.7\u202fGB" - ], - [ - "instruct", - "4.7\u202fGB" - ], - [ - "text", - "4.7\u202fGB" - ], - [ - "8b-instruct-fp16", - "17\u202fGB" - ], - [ - "8b-instruct-q2_K", - "3.5\u202fGB" - ], - [ - "8b-instruct-q3_K_S", - "3.6\u202fGB" - ], - [ - "8b-instruct-q3_K_M", - "4.1\u202fGB" - ], - [ - "8b-instruct-q3_K_L", - "4.5\u202fGB" - ], - [ - "8b-instruct-q4_0", - "4.7\u202fGB" - ], - [ - "8b-instruct-q4_1", - "5.3\u202fGB" - ], - [ - "8b-instruct-q4_K_S", - "4.8\u202fGB" - ], - [ - "8b-instruct-q4_K_M", - "5.1\u202fGB" - ], - [ - "8b-instruct-q5_0", - "5.8\u202fGB" - ], - [ - "8b-instruct-q5_1", - "6.3\u202fGB" - ], - [ - "8b-instruct-q5_K_S", - "5.8\u202fGB" - ], - [ - "8b-instruct-q5_K_M", - "5.9\u202fGB" - ], - [ - "8b-instruct-q6_K", - "6.9\u202fGB" - ], - [ - "8b-instruct-q8_0", - "8.9\u202fGB" - ], - [ - "8b-text-fp16", - "17\u202fGB" - ], - [ - "8b-text-q2_K", - "3.5\u202fGB" - ], - [ - "8b-text-q3_K_S", - "3.6\u202fGB" - ], - [ - "8b-text-q3_K_M", - "4.1\u202fGB" - ], - [ - "8b-text-q3_K_L", - "4.5\u202fGB" - ], - [ - "8b-text-q4_0", - "4.7\u202fGB" - ], - [ - "8b-text-q4_1", - "5.3\u202fGB" - ], - [ - "8b-text-q4_K_S", - "4.8\u202fGB" - ], - [ - "8b-text-q4_K_M", - "5.1\u202fGB" - ], - [ - "8b-text-q5_0", - "5.8\u202fGB" - ], - [ - "8b-text-q5_1", - "6.3\u202fGB" - ], - [ - "8b-text-q5_K_S", - "5.8\u202fGB" - ], - [ - "8b-text-q5_K_M", - "5.9\u202fGB" - ], - [ - "8b-text-q6_K", - "6.9\u202fGB" - ], - [ - "8b-text-q8_0", - "8.9\u202fGB" - ] - ], - "image": false, - "author": "Tencent" - }, "llava-phi3": { "url": "https://ollama.com/library/llava-phi3", "description": "A new small LLaVA model fine-tuned from Phi 3 Mini.", @@ -19751,482 +20043,6 @@ "image": false, "author": "Xtuner" }, - "meditron": { - "url": "https://ollama.com/library/meditron", - "description": "Open-source medical large language model adapted from Llama 2 to the medical domain.", - "tags": [ - [ - "latest", - "3.8\u202fGB" - ], - [ - "7b", - "3.8\u202fGB" - ], - [ - "70b", - "39\u202fGB" - ], - [ - "7b-fp16", - "13\u202fGB" - ], - [ - "7b-q2_K", - "2.8\u202fGB" - ], - [ - "7b-q3_K_S", - "2.9\u202fGB" - ], - [ - "7b-q3_K_M", - "3.3\u202fGB" - ], - [ - "7b-q3_K_L", - "3.6\u202fGB" - ], - [ - "7b-q4_0", - "3.8\u202fGB" - ], - [ - "7b-q4_1", - "4.2\u202fGB" - ], - [ - "7b-q4_K_S", - "3.9\u202fGB" - ], - [ - "7b-q4_K_M", - "4.1\u202fGB" - ], - [ - "7b-q5_0", - "4.7\u202fGB" - ], - [ - "7b-q5_1", - "5.1\u202fGB" - ], - [ - "7b-q5_K_S", - "4.7\u202fGB" - ], - [ - "7b-q5_K_M", - "4.8\u202fGB" - ], - [ - "7b-q6_K", - "5.5\u202fGB" - ], - [ - "7b-q8_0", - "7.2\u202fGB" - ], - [ - "70b-q4_0", - "39\u202fGB" - ], - [ - "70b-q4_1", - "43\u202fGB" - ], - [ - "70b-q4_K_S", - "39\u202fGB" - ], - [ - "70b-q5_1", - "52\u202fGB" - ] - ], - "image": false, - "author": "EPFL LLM Team" - }, - "nous-hermes2-mixtral": { - "url": "https://ollama.com/library/nous-hermes2-mixtral", - "description": "The Nous Hermes 2 model from Nous Research, now trained over Mixtral.", - "tags": [ - [ - "latest", - "26\u202fGB" - ], - [ - "8x7b", - "26\u202fGB" - ], - [ - "dpo", - "26\u202fGB" - ], - [ - "8x7b-dpo-fp16", - "93\u202fGB" - ], - [ - "8x7b-dpo-q2_K", - "16\u202fGB" - ], - [ - "8x7b-dpo-q3_K_S", - "20\u202fGB" - ], - [ - "8x7b-dpo-q3_K_M", - "20\u202fGB" - ], - [ - "8x7b-dpo-q3_K_L", - "20\u202fGB" - ], - [ - "8x7b-dpo-q4_0", - "26\u202fGB" - ], - [ - "8x7b-dpo-q4_1", - "29\u202fGB" - ], - [ - "8x7b-dpo-q4_K_S", - "26\u202fGB" - ], - [ - "8x7b-dpo-q4_K_M", - "26\u202fGB" - ], - [ - "8x7b-dpo-q5_0", - "32\u202fGB" - ], - [ - "8x7b-dpo-q5_1", - "35\u202fGB" - ], - [ - "8x7b-dpo-q5_K_S", - "32\u202fGB" - ], - [ - "8x7b-dpo-q5_K_M", - "32\u202fGB" - ], - [ - "8x7b-dpo-q6_K", - "38\u202fGB" - ], - [ - "8x7b-dpo-q8_0", - "50\u202fGB" - ] - ], - "image": false, - "author": "Nous Research" - }, - "nexusraven": { - "url": "https://ollama.com/library/nexusraven", - "description": "Nexus Raven is a 13B instruction tuned model for function calling tasks.", - "tags": [ - [ - "latest", - "7.4\u202fGB" - ], - [ - "13b", - "7.4\u202fGB" - ], - [ - "13b-fp16", - "26\u202fGB" - ], - [ - "13b-q2_K", - "5.4\u202fGB" - ], - [ - "13b-q3_K_S", - "5.7\u202fGB" - ], - [ - "13b-q3_K_M", - "6.3\u202fGB" - ], - [ - "13b-q3_K_L", - "6.9\u202fGB" - ], - [ - "13b-q4_0", - "7.4\u202fGB" - ], - [ - "13b-q4_1", - "8.2\u202fGB" - ], - [ - "13b-q4_K_S", - "7.4\u202fGB" - ], - [ - "13b-q4_K_M", - "7.9\u202fGB" - ], - [ - "13b-q5_0", - "9.0\u202fGB" - ], - [ - "13b-q5_1", - "9.8\u202fGB" - ], - [ - "13b-q5_K_S", - "9.0\u202fGB" - ], - [ - "13b-q5_K_M", - "9.2\u202fGB" - ], - [ - "13b-q6_K", - "11\u202fGB" - ], - [ - "13b-q8_0", - "14\u202fGB" - ], - [ - "13b-v2-fp16", - "26\u202fGB" - ], - [ - "13b-v2-q2_K", - "5.4\u202fGB" - ], - [ - "13b-v2-q3_K_S", - "5.7\u202fGB" - ], - [ - "13b-v2-q3_K_M", - "6.3\u202fGB" - ], - [ - "13b-v2-q3_K_L", - "6.9\u202fGB" - ], - [ - "13b-v2-q4_0", - "7.4\u202fGB" - ], - [ - "13b-v2-q4_1", - "8.2\u202fGB" - ], - [ - "13b-v2-q4_K_S", - "7.4\u202fGB" - ], - [ - "13b-v2-q4_K_M", - "7.9\u202fGB" - ], - [ - "13b-v2-q5_0", - "9.0\u202fGB" - ], - [ - "13b-v2-q5_1", - "9.8\u202fGB" - ], - [ - "13b-v2-q5_K_S", - "9.0\u202fGB" - ], - [ - "13b-v2-q5_K_M", - "9.2\u202fGB" - ], - [ - "13b-v2-q6_K", - "11\u202fGB" - ], - [ - "13b-v2-q8_0", - "14\u202fGB" - ] - ], - "image": false, - "author": "NexusFlow AI" - }, - "codeup": { - "url": "https://ollama.com/library/codeup", - "description": "Great code generation model based on Llama2.", - "tags": [ - [ - "latest", - "7.4\u202fGB" - ], - [ - "13b", - "7.4\u202fGB" - ], - [ - "13b-llama2", - "7.4\u202fGB" - ], - [ - "13b-llama2-chat", - "7.4\u202fGB" - ], - [ - "13b-llama2-chat-fp16", - "26\u202fGB" - ], - [ - "13b-llama2-chat-q2_K", - "5.4\u202fGB" - ], - [ - "13b-llama2-chat-q3_K_S", - "5.7\u202fGB" - ], - [ - "13b-llama2-chat-q3_K_M", - "6.3\u202fGB" - ], - [ - "13b-llama2-chat-q3_K_L", - "6.9\u202fGB" - ], - [ - "13b-llama2-chat-q4_0", - "7.4\u202fGB" - ], - [ - "13b-llama2-chat-q4_1", - "8.2\u202fGB" - ], - [ - "13b-llama2-chat-q4_K_S", - "7.4\u202fGB" - ], - [ - "13b-llama2-chat-q4_K_M", - "7.9\u202fGB" - ], - [ - "13b-llama2-chat-q5_0", - "9.0\u202fGB" - ], - [ - "13b-llama2-chat-q5_1", - "9.8\u202fGB" - ], - [ - "13b-llama2-chat-q5_K_S", - "9.0\u202fGB" - ], - [ - "13b-llama2-chat-q5_K_M", - "9.2\u202fGB" - ], - [ - "13b-llama2-chat-q6_K", - "11\u202fGB" - ], - [ - "13b-llama2-chat-q8_0", - "14\u202fGB" - ] - ], - "image": false, - "author": "DeepSE" - }, - "everythinglm": { - "url": "https://ollama.com/library/everythinglm", - "description": "Uncensored Llama2 based model with support for a 16K context window.", - "tags": [ - [ - "latest", - "7.4\u202fGB" - ], - [ - "13b", - "7.4\u202fGB" - ], - [ - "13b-16k", - "7.4\u202fGB" - ], - [ - "13b-16k-fp16", - "26\u202fGB" - ], - [ - "13b-16k-q2_K", - "5.4\u202fGB" - ], - [ - "13b-16k-q3_K_S", - "5.7\u202fGB" - ], - [ - "13b-16k-q3_K_M", - "6.3\u202fGB" - ], - [ - "13b-16k-q3_K_L", - "6.9\u202fGB" - ], - [ - "13b-16k-q4_0", - "7.4\u202fGB" - ], - [ - "13b-16k-q4_1", - "8.2\u202fGB" - ], - [ - "13b-16k-q4_K_S", - "7.4\u202fGB" - ], - [ - "13b-16k-q4_K_M", - "7.9\u202fGB" - ], - [ - "13b-16k-q5_0", - "9.0\u202fGB" - ], - [ - "13b-16k-q5_1", - "9.8\u202fGB" - ], - [ - "13b-16k-q5_K_S", - "9.0\u202fGB" - ], - [ - "13b-16k-q5_K_M", - "9.2\u202fGB" - ], - [ - "13b-16k-q6_K", - "11\u202fGB" - ], - [ - "13b-16k-q8_0", - "14\u202fGB" - ] - ], - "image": false, - "author": "Totally Not An LLM" - }, "hermes3": { "url": "https://ollama.com/library/hermes3", "description": "Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research", @@ -20429,8 +20245,640 @@ ] ], "image": false, + "author": "NousResearch" + }, + "yarn-mistral": { + "url": "https://ollama.com/library/yarn-mistral", + "description": "An extension of Mistral to support context windows of 64K or 128K.", + "tags": [ + [ + "latest", + "4.1\u202fGB" + ], + [ + "7b", + "4.1\u202fGB" + ], + [ + "7b-128k", + "4.1\u202fGB" + ], + [ + "7b-64k", + "4.1\u202fGB" + ], + [ + "7b-128k-fp16", + "14\u202fGB" + ], + [ + "7b-128k-q2_K", + "3.1\u202fGB" + ], + [ + "7b-128k-q3_K_S", + "3.2\u202fGB" + ], + [ + "7b-128k-q3_K_M", + "3.5\u202fGB" + ], + [ + "7b-128k-q3_K_L", + "3.8\u202fGB" + ], + [ + "7b-128k-q4_0", + "4.1\u202fGB" + ], + [ + "7b-128k-q4_1", + "4.6\u202fGB" + ], + [ + "7b-128k-q4_K_S", + "4.1\u202fGB" + ], + [ + "7b-128k-q4_K_M", + "4.4\u202fGB" + ], + [ + "7b-128k-q5_0", + "5.0\u202fGB" + ], + [ + "7b-128k-q5_1", + "5.4\u202fGB" + ], + [ + "7b-128k-q5_K_S", + "5.0\u202fGB" + ], + [ + "7b-128k-q5_K_M", + "5.1\u202fGB" + ], + [ + "7b-128k-q6_K", + "5.9\u202fGB" + ], + [ + "7b-128k-q8_0", + "7.7\u202fGB" + ], + [ + "7b-64k-q2_K", + "3.1\u202fGB" + ], + [ + "7b-64k-q3_K_S", + "3.2\u202fGB" + ], + [ + "7b-64k-q3_K_M", + "3.5\u202fGB" + ], + [ + "7b-64k-q3_K_L", + "3.8\u202fGB" + ], + [ + "7b-64k-q4_0", + "4.1\u202fGB" + ], + [ + "7b-64k-q4_1", + "4.6\u202fGB" + ], + [ + "7b-64k-q4_K_S", + "4.1\u202fGB" + ], + [ + "7b-64k-q4_K_M", + "4.4\u202fGB" + ], + [ + "7b-64k-q5_0", + "5.0\u202fGB" + ], + [ + "7b-64k-q5_1", + "5.4\u202fGB" + ], + [ + "7b-64k-q5_K_S", + "5.0\u202fGB" + ], + [ + "7b-64k-q5_K_M", + "5.1\u202fGB" + ], + [ + "7b-64k-q6_K", + "5.9\u202fGB" + ], + [ + "7b-64k-q8_0", + "7.7\u202fGB" + ] + ], + "image": false, "author": "Nous Research" }, + "llama-pro": { + "url": "https://ollama.com/library/llama-pro", + "description": "An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.", + "tags": [ + [ + "latest", + "4.7\u202fGB" + ], + [ + "instruct", + "4.7\u202fGB" + ], + [ + "text", + "4.7\u202fGB" + ], + [ + "8b-instruct-fp16", + "17\u202fGB" + ], + [ + "8b-instruct-q2_K", + "3.5\u202fGB" + ], + [ + "8b-instruct-q3_K_S", + "3.6\u202fGB" + ], + [ + "8b-instruct-q3_K_M", + "4.1\u202fGB" + ], + [ + "8b-instruct-q3_K_L", + "4.5\u202fGB" + ], + [ + "8b-instruct-q4_0", + "4.7\u202fGB" + ], + [ + "8b-instruct-q4_1", + "5.3\u202fGB" + ], + [ + "8b-instruct-q4_K_S", + "4.8\u202fGB" + ], + [ + "8b-instruct-q4_K_M", + "5.1\u202fGB" + ], + [ + "8b-instruct-q5_0", + "5.8\u202fGB" + ], + [ + "8b-instruct-q5_1", + "6.3\u202fGB" + ], + [ + "8b-instruct-q5_K_S", + "5.8\u202fGB" + ], + [ + "8b-instruct-q5_K_M", + "5.9\u202fGB" + ], + [ + "8b-instruct-q6_K", + "6.9\u202fGB" + ], + [ + "8b-instruct-q8_0", + "8.9\u202fGB" + ], + [ + "8b-text-fp16", + "17\u202fGB" + ], + [ + "8b-text-q2_K", + "3.5\u202fGB" + ], + [ + "8b-text-q3_K_S", + "3.6\u202fGB" + ], + [ + "8b-text-q3_K_M", + "4.1\u202fGB" + ], + [ + "8b-text-q3_K_L", + "4.5\u202fGB" + ], + [ + "8b-text-q4_0", + "4.7\u202fGB" + ], + [ + "8b-text-q4_1", + "5.3\u202fGB" + ], + [ + "8b-text-q4_K_S", + "4.8\u202fGB" + ], + [ + "8b-text-q4_K_M", + "5.1\u202fGB" + ], + [ + "8b-text-q5_0", + "5.8\u202fGB" + ], + [ + "8b-text-q5_1", + "6.3\u202fGB" + ], + [ + "8b-text-q5_K_S", + "5.8\u202fGB" + ], + [ + "8b-text-q5_K_M", + "5.9\u202fGB" + ], + [ + "8b-text-q6_K", + "6.9\u202fGB" + ], + [ + "8b-text-q8_0", + "8.9\u202fGB" + ] + ], + "image": false, + "author": "Tencent" + }, + "medllama2": { + "url": "https://ollama.com/library/medllama2", + "description": "Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.", + "tags": [ + [ + "latest", + "3.8\u202fGB" + ], + [ + "7b", + "3.8\u202fGB" + ], + [ + "7b-fp16", + "13\u202fGB" + ], + [ + "7b-q2_K", + "2.8\u202fGB" + ], + [ + "7b-q3_K_S", + "2.9\u202fGB" + ], + [ + "7b-q3_K_M", + "3.3\u202fGB" + ], + [ + "7b-q3_K_L", + "3.6\u202fGB" + ], + [ + "7b-q4_0", + "3.8\u202fGB" + ], + [ + "7b-q4_1", + "4.2\u202fGB" + ], + [ + "7b-q4_K_S", + "3.9\u202fGB" + ], + [ + "7b-q4_K_M", + "4.1\u202fGB" + ], + [ + "7b-q5_0", + "4.7\u202fGB" + ], + [ + "7b-q5_1", + "5.1\u202fGB" + ], + [ + "7b-q5_K_S", + "4.7\u202fGB" + ], + [ + "7b-q5_K_M", + "4.8\u202fGB" + ], + [ + "7b-q6_K", + "5.5\u202fGB" + ], + [ + "7b-q8_0", + "7.2\u202fGB" + ] + ], + "image": false, + "author": "Siraj Raval" + }, + "yi-coder": { + "url": "https://ollama.com/library/yi-coder", + "description": "Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.", + "tags": [ + [ + "latest", + "5.0\u202fGB" + ], + [ + "1.5b", + "866\u202fMB" + ], + [ + "9b", + "5.0\u202fGB" + ], + [ + "1.5b-base", + "866\u202fMB" + ], + [ + "1.5b-chat", + "866\u202fMB" + ], + [ + "9b-base", + "5.0\u202fGB" + ], + [ + "9b-chat", + "5.0\u202fGB" + ], + [ + "1.5b-base-fp16", + "3.0\u202fGB" + ], + [ + "1.5b-base-q2_K", + "635\u202fMB" + ], + [ + "1.5b-base-q3_K_S", + "723\u202fMB" + ], + [ + "1.5b-base-q3_K_M", + "786\u202fMB" + ], + [ + "1.5b-base-q3_K_L", + "826\u202fMB" + ], + [ + "1.5b-base-q4_0", + "866\u202fMB" + ], + [ + "1.5b-base-q4_1", + "950\u202fMB" + ], + [ + "1.5b-base-q4_K_S", + "904\u202fMB" + ], + [ + "1.5b-base-q4_K_M", + "964\u202fMB" + ], + [ + "1.5b-base-q5_0", + "1.0\u202fGB" + ], + [ + "1.5b-base-q5_1", + "1.1\u202fGB" + ], + [ + "1.5b-base-q5_K_S", + "1.1\u202fGB" + ], + [ + "1.5b-base-q5_K_M", + "1.1\u202fGB" + ], + [ + "1.5b-base-q6_K", + "1.3\u202fGB" + ], + [ + "1.5b-base-q8_0", + "1.6\u202fGB" + ], + [ + "1.5b-chat-fp16", + "3.0\u202fGB" + ], + [ + "1.5b-chat-q2_K", + "635\u202fMB" + ], + [ + "1.5b-chat-q3_K_S", + "723\u202fMB" + ], + [ + "1.5b-chat-q3_K_M", + "786\u202fMB" + ], + [ + "1.5b-chat-q3_K_L", + "826\u202fMB" + ], + [ + "1.5b-chat-q4_0", + "866\u202fMB" + ], + [ + "1.5b-chat-q4_1", + "950\u202fMB" + ], + [ + "1.5b-chat-q4_K_S", + "904\u202fMB" + ], + [ + "1.5b-chat-q4_K_M", + "964\u202fMB" + ], + [ + "1.5b-chat-q5_0", + "1.0\u202fGB" + ], + [ + "1.5b-chat-q5_1", + "1.1\u202fGB" + ], + [ + "1.5b-chat-q5_K_S", + "1.1\u202fGB" + ], + [ + "1.5b-chat-q5_K_M", + "1.1\u202fGB" + ], + [ + "1.5b-chat-q6_K", + "1.3\u202fGB" + ], + [ + "1.5b-chat-q8_0", + "1.6\u202fGB" + ], + [ + "9b-base-fp16", + "18\u202fGB" + ], + [ + "9b-base-q2_K", + "3.4\u202fGB" + ], + [ + "9b-base-q3_K_S", + "3.9\u202fGB" + ], + [ + "9b-base-q3_K_M", + "4.3\u202fGB" + ], + [ + "9b-base-q3_K_L", + "4.7\u202fGB" + ], + [ + "9b-base-q4_0", + "5.0\u202fGB" + ], + [ + "9b-base-q4_1", + "5.6\u202fGB" + ], + [ + "9b-base-q4_K_S", + "5.1\u202fGB" + ], + [ + "9b-base-q4_K_M", + "5.3\u202fGB" + ], + [ + "9b-base-q5_0", + "6.1\u202fGB" + ], + [ + "9b-base-q5_1", + "6.6\u202fGB" + ], + [ + "9b-base-q5_K_S", + "6.1\u202fGB" + ], + [ + "9b-base-q5_K_M", + "6.3\u202fGB" + ], + [ + "9b-base-q6_K", + "7.2\u202fGB" + ], + [ + "9b-base-q8_0", + "9.4\u202fGB" + ], + [ + "9b-chat-fp16", + "18\u202fGB" + ], + [ + "9b-chat-q2_K", + "3.4\u202fGB" + ], + [ + "9b-chat-q3_K_S", + "3.9\u202fGB" + ], + [ + "9b-chat-q3_K_M", + "4.3\u202fGB" + ], + [ + "9b-chat-q3_K_L", + "4.7\u202fGB" + ], + [ + "9b-chat-q4_0", + "5.0\u202fGB" + ], + [ + "9b-chat-q4_1", + "5.6\u202fGB" + ], + [ + "9b-chat-q4_K_S", + "5.1\u202fGB" + ], + [ + "9b-chat-q4_K_M", + "5.3\u202fGB" + ], + [ + "9b-chat-q5_0", + "6.1\u202fGB" + ], + [ + "9b-chat-q5_1", + "6.6\u202fGB" + ], + [ + "9b-chat-q5_K_S", + "6.1\u202fGB" + ], + [ + "9b-chat-q5_K_M", + "6.3\u202fGB" + ], + [ + "9b-chat-q6_K", + "7.2\u202fGB" + ], + [ + "9b-chat-q8_0", + "9.4\u202fGB" + ] + ], + "image": false, + "author": "01-AI" + }, "internlm2": { "url": "https://ollama.com/library/internlm2", "description": "InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability.", @@ -20699,6 +21147,622 @@ "image": false, "author": "Intern LM" }, + "meditron": { + "url": "https://ollama.com/library/meditron", + "description": "Open-source medical large language model adapted from Llama 2 to the medical domain.", + "tags": [ + [ + "latest", + "3.8\u202fGB" + ], + [ + "7b", + "3.8\u202fGB" + ], + [ + "70b", + "39\u202fGB" + ], + [ + "7b-fp16", + "13\u202fGB" + ], + [ + "7b-q2_K", + "2.8\u202fGB" + ], + [ + "7b-q3_K_S", + "2.9\u202fGB" + ], + [ + "7b-q3_K_M", + "3.3\u202fGB" + ], + [ + "7b-q3_K_L", + "3.6\u202fGB" + ], + [ + "7b-q4_0", + "3.8\u202fGB" + ], + [ + "7b-q4_1", + "4.2\u202fGB" + ], + [ + "7b-q4_K_S", + "3.9\u202fGB" + ], + [ + "7b-q4_K_M", + "4.1\u202fGB" + ], + [ + "7b-q5_0", + "4.7\u202fGB" + ], + [ + "7b-q5_1", + "5.1\u202fGB" + ], + [ + "7b-q5_K_S", + "4.7\u202fGB" + ], + [ + "7b-q5_K_M", + "4.8\u202fGB" + ], + [ + "7b-q6_K", + "5.5\u202fGB" + ], + [ + "7b-q8_0", + "7.2\u202fGB" + ], + [ + "70b-q4_0", + "39\u202fGB" + ], + [ + "70b-q4_1", + "43\u202fGB" + ], + [ + "70b-q4_K_S", + "39\u202fGB" + ], + [ + "70b-q5_1", + "52\u202fGB" + ] + ], + "image": false, + "author": "EPFL LLM Team" + }, + "nexusraven": { + "url": "https://ollama.com/library/nexusraven", + "description": "Nexus Raven is a 13B instruction tuned model for function calling tasks.", + "tags": [ + [ + "latest", + "7.4\u202fGB" + ], + [ + "13b", + "7.4\u202fGB" + ], + [ + "13b-fp16", + "26\u202fGB" + ], + [ + "13b-q2_K", + "5.4\u202fGB" + ], + [ + "13b-q3_K_S", + "5.7\u202fGB" + ], + [ + "13b-q3_K_M", + "6.3\u202fGB" + ], + [ + "13b-q3_K_L", + "6.9\u202fGB" + ], + [ + "13b-q4_0", + "7.4\u202fGB" + ], + [ + "13b-q4_1", + "8.2\u202fGB" + ], + [ + "13b-q4_K_S", + "7.4\u202fGB" + ], + [ + "13b-q4_K_M", + "7.9\u202fGB" + ], + [ + "13b-q5_0", + "9.0\u202fGB" + ], + [ + "13b-q5_1", + "9.8\u202fGB" + ], + [ + "13b-q5_K_S", + "9.0\u202fGB" + ], + [ + "13b-q5_K_M", + "9.2\u202fGB" + ], + [ + "13b-q6_K", + "11\u202fGB" + ], + [ + "13b-q8_0", + "14\u202fGB" + ], + [ + "13b-v2-fp16", + "26\u202fGB" + ], + [ + "13b-v2-q2_K", + "5.4\u202fGB" + ], + [ + "13b-v2-q3_K_S", + "5.7\u202fGB" + ], + [ + "13b-v2-q3_K_M", + "6.3\u202fGB" + ], + [ + "13b-v2-q3_K_L", + "6.9\u202fGB" + ], + [ + "13b-v2-q4_0", + "7.4\u202fGB" + ], + [ + "13b-v2-q4_1", + "8.2\u202fGB" + ], + [ + "13b-v2-q4_K_S", + "7.4\u202fGB" + ], + [ + "13b-v2-q4_K_M", + "7.9\u202fGB" + ], + [ + "13b-v2-q5_0", + "9.0\u202fGB" + ], + [ + "13b-v2-q5_1", + "9.8\u202fGB" + ], + [ + "13b-v2-q5_K_S", + "9.0\u202fGB" + ], + [ + "13b-v2-q5_K_M", + "9.2\u202fGB" + ], + [ + "13b-v2-q6_K", + "11\u202fGB" + ], + [ + "13b-v2-q8_0", + "14\u202fGB" + ] + ], + "image": false, + "author": "NexusFlow AI" + }, + "nous-hermes2-mixtral": { + "url": "https://ollama.com/library/nous-hermes2-mixtral", + "description": "The Nous Hermes 2 model from Nous Research, now trained over Mixtral.", + "tags": [ + [ + "latest", + "26\u202fGB" + ], + [ + "8x7b", + "26\u202fGB" + ], + [ + "dpo", + "26\u202fGB" + ], + [ + "8x7b-dpo-fp16", + "93\u202fGB" + ], + [ + "8x7b-dpo-q2_K", + "16\u202fGB" + ], + [ + "8x7b-dpo-q3_K_S", + "20\u202fGB" + ], + [ + "8x7b-dpo-q3_K_M", + "20\u202fGB" + ], + [ + "8x7b-dpo-q3_K_L", + "20\u202fGB" + ], + [ + "8x7b-dpo-q4_0", + "26\u202fGB" + ], + [ + "8x7b-dpo-q4_1", + "29\u202fGB" + ], + [ + "8x7b-dpo-q4_K_S", + "26\u202fGB" + ], + [ + "8x7b-dpo-q4_K_M", + "26\u202fGB" + ], + [ + "8x7b-dpo-q5_0", + "32\u202fGB" + ], + [ + "8x7b-dpo-q5_1", + "35\u202fGB" + ], + [ + "8x7b-dpo-q5_K_S", + "32\u202fGB" + ], + [ + "8x7b-dpo-q5_K_M", + "32\u202fGB" + ], + [ + "8x7b-dpo-q6_K", + "38\u202fGB" + ], + [ + "8x7b-dpo-q8_0", + "50\u202fGB" + ] + ], + "image": false, + "author": "Nous Research" + }, + "codeup": { + "url": "https://ollama.com/library/codeup", + "description": "Great code generation model based on Llama2.", + "tags": [ + [ + "latest", + "7.4\u202fGB" + ], + [ + "13b", + "7.4\u202fGB" + ], + [ + "13b-llama2", + "7.4\u202fGB" + ], + [ + "13b-llama2-chat", + "7.4\u202fGB" + ], + [ + "13b-llama2-chat-fp16", + "26\u202fGB" + ], + [ + "13b-llama2-chat-q2_K", + "5.4\u202fGB" + ], + [ + "13b-llama2-chat-q3_K_S", + "5.7\u202fGB" + ], + [ + "13b-llama2-chat-q3_K_M", + "6.3\u202fGB" + ], + [ + "13b-llama2-chat-q3_K_L", + "6.9\u202fGB" + ], + [ + "13b-llama2-chat-q4_0", + "7.4\u202fGB" + ], + [ + "13b-llama2-chat-q4_1", + "8.2\u202fGB" + ], + [ + "13b-llama2-chat-q4_K_S", + "7.4\u202fGB" + ], + [ + "13b-llama2-chat-q4_K_M", + "7.9\u202fGB" + ], + [ + "13b-llama2-chat-q5_0", + "9.0\u202fGB" + ], + [ + "13b-llama2-chat-q5_1", + "9.8\u202fGB" + ], + [ + "13b-llama2-chat-q5_K_S", + "9.0\u202fGB" + ], + [ + "13b-llama2-chat-q5_K_M", + "9.2\u202fGB" + ], + [ + "13b-llama2-chat-q6_K", + "11\u202fGB" + ], + [ + "13b-llama2-chat-q8_0", + "14\u202fGB" + ] + ], + "image": false, + "author": "DeepSE" + }, + "everythinglm": { + "url": "https://ollama.com/library/everythinglm", + "description": "Uncensored Llama2 based model with support for a 16K context window.", + "tags": [ + [ + "latest", + "7.4\u202fGB" + ], + [ + "13b", + "7.4\u202fGB" + ], + [ + "13b-16k", + "7.4\u202fGB" + ], + [ + "13b-16k-fp16", + "26\u202fGB" + ], + [ + "13b-16k-q2_K", + "5.4\u202fGB" + ], + [ + "13b-16k-q3_K_S", + "5.7\u202fGB" + ], + [ + "13b-16k-q3_K_M", + "6.3\u202fGB" + ], + [ + "13b-16k-q3_K_L", + "6.9\u202fGB" + ], + [ + "13b-16k-q4_0", + "7.4\u202fGB" + ], + [ + "13b-16k-q4_1", + "8.2\u202fGB" + ], + [ + "13b-16k-q4_K_S", + "7.4\u202fGB" + ], + [ + "13b-16k-q4_K_M", + "7.9\u202fGB" + ], + [ + "13b-16k-q5_0", + "9.0\u202fGB" + ], + [ + "13b-16k-q5_1", + "9.8\u202fGB" + ], + [ + "13b-16k-q5_K_S", + "9.0\u202fGB" + ], + [ + "13b-16k-q5_K_M", + "9.2\u202fGB" + ], + [ + "13b-16k-q6_K", + "11\u202fGB" + ], + [ + "13b-16k-q8_0", + "14\u202fGB" + ] + ], + "image": false, + "author": "Totally Not An LLM" + }, + "llama3-groq-tool-use": { + "url": "https://ollama.com/library/llama3-groq-tool-use", + "description": "A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.", + "tags": [ + [ + "latest", + "4.7\u202fGB" + ], + [ + "8b", + "4.7\u202fGB" + ], + [ + "70b", + "40\u202fGB" + ], + [ + "8b-fp16", + "16\u202fGB" + ], + [ + "8b-q2_K", + "3.2\u202fGB" + ], + [ + "8b-q3_K_S", + "3.7\u202fGB" + ], + [ + "8b-q3_K_M", + "4.0\u202fGB" + ], + [ + "8b-q3_K_L", + "4.3\u202fGB" + ], + [ + "8b-q4_0", + "4.7\u202fGB" + ], + [ + "8b-q4_1", + "5.1\u202fGB" + ], + [ + "8b-q4_K_S", + "4.7\u202fGB" + ], + [ + "8b-q4_K_M", + "4.9\u202fGB" + ], + [ + "8b-q5_0", + "5.6\u202fGB" + ], + [ + "8b-q5_1", + "6.1\u202fGB" + ], + [ + "8b-q5_K_S", + "5.6\u202fGB" + ], + [ + "8b-q5_K_M", + "5.7\u202fGB" + ], + [ + "8b-q6_K", + "6.6\u202fGB" + ], + [ + "8b-q8_0", + "8.5\u202fGB" + ], + [ + "70b-fp16", + "141\u202fGB" + ], + [ + "70b-q2_K", + "26\u202fGB" + ], + [ + "70b-q3_K_S", + "31\u202fGB" + ], + [ + "70b-q3_K_M", + "34\u202fGB" + ], + [ + "70b-q3_K_L", + "37\u202fGB" + ], + [ + "70b-q4_0", + "40\u202fGB" + ], + [ + "70b-q4_1", + "44\u202fGB" + ], + [ + "70b-q4_K_S", + "40\u202fGB" + ], + [ + "70b-q4_K_M", + "43\u202fGB" + ], + [ + "70b-q5_0", + "49\u202fGB" + ], + [ + "70b-q5_1", + "53\u202fGB" + ], + [ + "70b-q5_K_S", + "49\u202fGB" + ], + [ + "70b-q5_K_M", + "50\u202fGB" + ], + [ + "70b-q6_K", + "58\u202fGB" + ], + [ + "70b-q8_0", + "75\u202fGB" + ] + ], + "image": false, + "author": "Groq" + }, "magicoder": { "url": "https://ollama.com/library/magicoder", "description": "\ud83c\udfa9 Magicoder is a family of 7B parameter models trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets.", @@ -21003,146 +22067,6 @@ "image": false, "author": "Amazon Web Services" }, - "llama3-groq-tool-use": { - "url": "https://ollama.com/library/llama3-groq-tool-use", - "description": "A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.", - "tags": [ - [ - "latest", - "4.7\u202fGB" - ], - [ - "8b", - "4.7\u202fGB" - ], - [ - "70b", - "40\u202fGB" - ], - [ - "8b-fp16", - "16\u202fGB" - ], - [ - "8b-q2_K", - "3.2\u202fGB" - ], - [ - "8b-q3_K_S", - "3.7\u202fGB" - ], - [ - "8b-q3_K_M", - "4.0\u202fGB" - ], - [ - "8b-q3_K_L", - "4.3\u202fGB" - ], - [ - "8b-q4_0", - "4.7\u202fGB" - ], - [ - "8b-q4_1", - "5.1\u202fGB" - ], - [ - "8b-q4_K_S", - "4.7\u202fGB" - ], - [ - "8b-q4_K_M", - "4.9\u202fGB" - ], - [ - "8b-q5_0", - "5.6\u202fGB" - ], - [ - "8b-q5_1", - "6.1\u202fGB" - ], - [ - "8b-q5_K_S", - "5.6\u202fGB" - ], - [ - "8b-q5_K_M", - "5.7\u202fGB" - ], - [ - "8b-q6_K", - "6.6\u202fGB" - ], - [ - "8b-q8_0", - "8.5\u202fGB" - ], - [ - "70b-fp16", - "141\u202fGB" - ], - [ - "70b-q2_K", - "26\u202fGB" - ], - [ - "70b-q3_K_S", - "31\u202fGB" - ], - [ - "70b-q3_K_M", - "34\u202fGB" - ], - [ - "70b-q3_K_L", - "37\u202fGB" - ], - [ - "70b-q4_0", - "40\u202fGB" - ], - [ - "70b-q4_1", - "44\u202fGB" - ], - [ - "70b-q4_K_S", - "40\u202fGB" - ], - [ - "70b-q4_K_M", - "43\u202fGB" - ], - [ - "70b-q5_0", - "49\u202fGB" - ], - [ - "70b-q5_1", - "53\u202fGB" - ], - [ - "70b-q5_K_S", - "49\u202fGB" - ], - [ - "70b-q5_K_M", - "50\u202fGB" - ], - [ - "70b-q6_K", - "58\u202fGB" - ], - [ - "70b-q8_0", - "75\u202fGB" - ] - ], - "image": false, - "author": "Groq" - }, "falcon2": { "url": "https://ollama.com/library/falcon2", "description": "Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens.", @@ -21371,6 +22295,282 @@ "image": false, "author": "MotherDuck, Numbers Station" }, + "qwen2.5-coder": { + "url": "https://ollama.com/library/qwen2.5-coder", + "description": "The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.", + "tags": [ + [ + "latest", + "4.7\u202fGB" + ], + [ + "1.5b", + "986\u202fMB" + ], + [ + "7b", + "4.7\u202fGB" + ], + [ + "1.5b-base", + "986\u202fMB" + ], + [ + "1.5b-instruct", + "986\u202fMB" + ], + [ + "7b-base", + "4.7\u202fGB" + ], + [ + "7b-instruct", + "4.7\u202fGB" + ], + [ + "1.5b-base-fp16", + "3.1\u202fGB" + ], + [ + "1.5b-base-q2_K", + "676\u202fMB" + ], + [ + "1.5b-base-q3_K_S", + "761\u202fMB" + ], + [ + "1.5b-base-q3_K_M", + "824\u202fMB" + ], + [ + "1.5b-base-q3_K_L", + "880\u202fMB" + ], + [ + "1.5b-base-q4_0", + "935\u202fMB" + ], + [ + "1.5b-base-q4_1", + "1.0\u202fGB" + ], + [ + "1.5b-base-q4_K_S", + "940\u202fMB" + ], + [ + "1.5b-base-q4_K_M", + "986\u202fMB" + ], + [ + "1.5b-base-q5_0", + "1.1\u202fGB" + ], + [ + "1.5b-base-q5_1", + "1.2\u202fGB" + ], + [ + "1.5b-base-q5_K_S", + "1.1\u202fGB" + ], + [ + "1.5b-base-q5_K_M", + "1.1\u202fGB" + ], + [ + "1.5b-base-q6_K", + "1.3\u202fGB" + ], + [ + "1.5b-base-q8_0", + "1.6\u202fGB" + ], + [ + "1.5b-instruct-fp16", + "3.1\u202fGB" + ], + [ + "1.5b-instruct-q2_K", + "676\u202fMB" + ], + [ + "1.5b-instruct-q3_K_S", + "761\u202fMB" + ], + [ + "1.5b-instruct-q3_K_M", + "824\u202fMB" + ], + [ + "1.5b-instruct-q3_K_L", + "880\u202fMB" + ], + [ + "1.5b-instruct-q4_0", + "935\u202fMB" + ], + [ + "1.5b-instruct-q4_1", + "1.0\u202fGB" + ], + [ + "1.5b-instruct-q4_K_S", + "940\u202fMB" + ], + [ + "1.5b-instruct-q4_K_M", + "986\u202fMB" + ], + [ + "1.5b-instruct-q5_0", + "1.1\u202fGB" + ], + [ + "1.5b-instruct-q5_1", + "1.2\u202fGB" + ], + [ + "1.5b-instruct-q5_K_S", + "1.1\u202fGB" + ], + [ + "1.5b-instruct-q5_K_M", + "1.1\u202fGB" + ], + [ + "1.5b-instruct-q6_K", + "1.3\u202fGB" + ], + [ + "1.5b-instruct-q8_0", + "1.6\u202fGB" + ], + [ + "7b-base-fp16", + "15\u202fGB" + ], + [ + "7b-base-q2_K", + "3.0\u202fGB" + ], + [ + "7b-base-q3_K_S", + "3.5\u202fGB" + ], + [ + "7b-base-q3_K_M", + "3.8\u202fGB" + ], + [ + "7b-base-q3_K_L", + "4.1\u202fGB" + ], + [ + "7b-base-q4_0", + "4.4\u202fGB" + ], + [ + "7b-base-q4_1", + "4.9\u202fGB" + ], + [ + "7b-base-q4_K_S", + "4.5\u202fGB" + ], + [ + "7b-base-q4_K_M", + "4.7\u202fGB" + ], + [ + "7b-base-q5_0", + "5.3\u202fGB" + ], + [ + "7b-base-q5_1", + "5.8\u202fGB" + ], + [ + "7b-base-q5_K_S", + "5.3\u202fGB" + ], + [ + "7b-base-q5_K_M", + "5.4\u202fGB" + ], + [ + "7b-base-q6_K", + "6.3\u202fGB" + ], + [ + "7b-base-q8_0", + "8.1\u202fGB" + ], + [ + "7b-instruct-fp16", + "15\u202fGB" + ], + [ + "7b-instruct-q2_K", + "3.0\u202fGB" + ], + [ + "7b-instruct-q3_K_S", + "3.5\u202fGB" + ], + [ + "7b-instruct-q3_K_M", + "3.8\u202fGB" + ], + [ + "7b-instruct-q3_K_L", + "4.1\u202fGB" + ], + [ + "7b-instruct-q4_0", + "4.4\u202fGB" + ], + [ + "7b-instruct-q4_1", + "4.9\u202fGB" + ], + [ + "7b-instruct-q4_K_S", + "4.5\u202fGB" + ], + [ + "7b-instruct-q4_K_M", + "4.7\u202fGB" + ], + [ + "7b-instruct-q5_0", + "5.3\u202fGB" + ], + [ + "7b-instruct-q5_1", + "5.8\u202fGB" + ], + [ + "7b-instruct-q5_K_S", + "5.3\u202fGB" + ], + [ + "7b-instruct-q5_K_M", + "5.4\u202fGB" + ], + [ + "7b-instruct-q6_K", + "6.3\u202fGB" + ], + [ + "7b-instruct-q8_0", + "8.1\u202fGB" + ] + ], + "image": false, + "author": "Alibaba" + }, "megadolphin": { "url": "https://ollama.com/library/megadolphin", "description": "MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself.", @@ -21763,41 +22963,25 @@ "image": false, "author": "Argilla" }, - "dbrx": { - "url": "https://ollama.com/library/dbrx", - "description": "DBRX is an open, general-purpose LLM created by Databricks.", + "bge-m3": { + "url": "https://ollama.com/library/bge-m3", + "description": "BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.", "tags": [ [ "latest", - "74\u202fGB" + "1.2\u202fGB" ], [ - "132b", - "74\u202fGB" + "567m", + "1.2\u202fGB" ], [ - "instruct", - "74\u202fGB" - ], - [ - "132b-instruct-fp16", - "263\u202fGB" - ], - [ - "132b-instruct-q2_K", - "48\u202fGB" - ], - [ - "132b-instruct-q4_0", - "74\u202fGB" - ], - [ - "132b-instruct-q8_0", - "140\u202fGB" + "567m-fp16", + "1.2\u202fGB" ] ], "image": false, - "author": "Databricks" + "author": "Bge M3 Team" }, "mathstral": { "url": "https://ollama.com/library/mathstral", @@ -21875,25 +23059,193 @@ "image": false, "author": "Mistral AI" }, - "bge-m3": { - "url": "https://ollama.com/library/bge-m3", - "description": "BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.", + "dbrx": { + "url": "https://ollama.com/library/dbrx", + "description": "DBRX is an open, general-purpose LLM created by Databricks.", "tags": [ [ "latest", - "1.2\u202fGB" + "74\u202fGB" ], [ - "567m", - "1.2\u202fGB" + "132b", + "74\u202fGB" ], [ - "567m-fp16", - "1.2\u202fGB" + "instruct", + "74\u202fGB" + ], + [ + "132b-instruct-fp16", + "263\u202fGB" + ], + [ + "132b-instruct-q2_K", + "48\u202fGB" + ], + [ + "132b-instruct-q4_0", + "74\u202fGB" + ], + [ + "132b-instruct-q8_0", + "140\u202fGB" ] ], "image": false, - "author": "BGE Team" + "author": "Databricks" + }, + "minicpm-v": { + "url": "https://ollama.com/library/minicpm-v", + "description": "A series of multimodal LLMs (MLLMs) designed for vision-language understanding.", + "tags": [ + [ + "latest", + "5.5\u202fGB" + ], + [ + "8b", + "5.5\u202fGB" + ], + [ + "8b-2.6-fp16", + "16\u202fGB" + ], + [ + "8b-2.6-q2_K", + "4.1\u202fGB" + ], + [ + "8b-2.6-q3_K_S", + "4.5\u202fGB" + ], + [ + "8b-2.6-q3_K_M", + "4.9\u202fGB" + ], + [ + "8b-2.6-q3_K_L", + "5.1\u202fGB" + ], + [ + "8b-2.6-q4_0", + "5.5\u202fGB" + ], + [ + "8b-2.6-q4_1", + "5.9\u202fGB" + ], + [ + "8b-2.6-q4_K_S", + "5.5\u202fGB" + ], + [ + "8b-2.6-q4_K_M", + "5.7\u202fGB" + ], + [ + "8b-2.6-q5_0", + "6.4\u202fGB" + ], + [ + "8b-2.6-q5_1", + "6.8\u202fGB" + ], + [ + "8b-2.6-q5_K_S", + "6.4\u202fGB" + ], + [ + "8b-2.6-q5_K_M", + "6.5\u202fGB" + ], + [ + "8b-2.6-q6_K", + "7.3\u202fGB" + ], + [ + "8b-2.6-q8_0", + "9.1\u202fGB" + ] + ], + "image": false, + "author": "OpenBMB" + }, + "nuextract": { + "url": "https://ollama.com/library/nuextract", + "description": "A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, based on Phi-3.", + "tags": [ + [ + "latest", + "2.2\u202fGB" + ], + [ + "3.8b", + "2.2\u202fGB" + ], + [ + "3.8b-fp16", + "7.6\u202fGB" + ], + [ + "3.8b-q2_K", + "1.4\u202fGB" + ], + [ + "3.8b-q3_K_S", + "1.7\u202fGB" + ], + [ + "3.8b-q3_K_M", + "2.0\u202fGB" + ], + [ + "3.8b-q3_K_L", + "2.1\u202fGB" + ], + [ + "3.8b-q4_0", + "2.2\u202fGB" + ], + [ + "3.8b-q4_1", + "2.4\u202fGB" + ], + [ + "3.8b-q4_K_S", + "2.2\u202fGB" + ], + [ + "3.8b-q4_K_M", + "2.4\u202fGB" + ], + [ + "3.8b-q5_0", + "2.6\u202fGB" + ], + [ + "3.8b-q5_1", + "2.9\u202fGB" + ], + [ + "3.8b-q5_K_S", + "2.6\u202fGB" + ], + [ + "3.8b-q5_K_M", + "2.8\u202fGB" + ], + [ + "3.8b-q6_K", + "3.1\u202fGB" + ], + [ + "3.8b-q8_0", + "4.1\u202fGB" + ] + ], + "image": false, + "author": "Numind" }, "alfred": { "url": "https://ollama.com/library/alfred", @@ -22007,81 +23359,85 @@ "image": false, "author": "Fireworks AI" }, - "nuextract": { - "url": "https://ollama.com/library/nuextract", - "description": "A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, based on Phi-3.", + "solar-pro": { + "url": "https://ollama.com/library/solar-pro", + "description": "Solar Pro Preview: an advanced large language model (LLM) with 22 billion parameters designed to fit into a single GPU", "tags": [ [ "latest", - "2.2\u202fGB" + "13\u202fGB" ], [ - "3.8b", - "2.2\u202fGB" + "22b", + "13\u202fGB" ], [ - "3.8b-fp16", - "7.6\u202fGB" + "preview", + "13\u202fGB" ], [ - "3.8b-q2_K", - "1.4\u202fGB" + "22b-preview-instruct-fp16", + "44\u202fGB" ], [ - "3.8b-q3_K_S", - "1.7\u202fGB" + "22b-preview-instruct-q2_K", + "8.2\u202fGB" ], [ - "3.8b-q3_K_M", - "2.0\u202fGB" + "22b-preview-instruct-q3_K_S", + "9.6\u202fGB" ], [ - "3.8b-q3_K_L", - "2.1\u202fGB" + "22b-preview-instruct-q3_K_M", + "11\u202fGB" ], [ - "3.8b-q4_0", - "2.2\u202fGB" + "22b-preview-instruct-q3_K_L", + "12\u202fGB" ], [ - "3.8b-q4_1", - "2.4\u202fGB" + "22b-preview-instruct-q4_0", + "12\u202fGB" ], [ - "3.8b-q4_K_S", - "2.2\u202fGB" + "22b-preview-instruct-q4_1", + "14\u202fGB" ], [ - "3.8b-q4_K_M", - "2.4\u202fGB" + "22b-preview-instruct-q4_K_S", + "13\u202fGB" ], [ - "3.8b-q5_0", - "2.6\u202fGB" + "22b-preview-instruct-q4_K_M", + "13\u202fGB" ], [ - "3.8b-q5_1", - "2.9\u202fGB" + "22b-preview-instruct-q5_0", + "15\u202fGB" ], [ - "3.8b-q5_K_S", - "2.6\u202fGB" + "22b-preview-instruct-q5_1", + "17\u202fGB" ], [ - "3.8b-q5_K_M", - "2.8\u202fGB" + "22b-preview-instruct-q5_K_S", + "15\u202fGB" ], [ - "3.8b-q6_K", - "3.1\u202fGB" + "22b-preview-instruct-q5_K_M", + "16\u202fGB" ], [ - "3.8b-q8_0", - "4.1\u202fGB" + "22b-preview-instruct-q6_K", + "18\u202fGB" + ], + [ + "22b-preview-instruct-q8_0", + "24\u202fGB" ] ], "image": false, - "author": "Numind" + "author": "Upstage" }, "bge-large": { "url": "https://ollama.com/library/bge-large", @@ -22101,7 +23457,183 @@ ] ], "image": false, - "author": "BGE Team" + "author": "Bge Large Team" + }, + "reader-lm": { + "url": "https://ollama.com/library/reader-lm", + "description": "A series of models that convert HTML content to Markdown content, which is useful for content conversion tasks.", + "tags": [ + [ + "latest", + "935\u202fMB" + ], + [ + "0.5b", + "352\u202fMB" + ], + [ + "1.5b", + "935\u202fMB" + ], + [ + "0.5b-fp16", + "994\u202fMB" + ], + [ + "0.5b-q2_K", + "339\u202fMB" + ], + [ + "0.5b-q3_K_S", + "338\u202fMB" + ], + [ + "0.5b-q3_K_M", + "355\u202fMB" + ], + [ + "0.5b-q3_K_L", + "369\u202fMB" + ], + [ + "0.5b-q4_0", + "352\u202fMB" + ], + [ + "0.5b-q4_1", + "375\u202fMB" + ], + [ + "0.5b-q4_K_S", + "385\u202fMB" + ], + [ + "0.5b-q4_K_M", + "398\u202fMB" + ], + [ + "0.5b-q5_0", + "397\u202fMB" + ], + [ + "0.5b-q5_1", + "419\u202fMB" + ], + [ + "0.5b-q5_K_S", + "413\u202fMB" + ], + [ + "0.5b-q5_K_M", + "420\u202fMB" + ], + [ + "0.5b-q6_K", + "506\u202fMB" + ], + [ + "0.5b-q8_0", + "531\u202fMB" + ], + [ + "1.5b-fp16", + "3.1\u202fGB" + ], + [ + "1.5b-q2_K", + "676\u202fMB" + ], + [ + "1.5b-q3_K_S", + "761\u202fMB" + ], + [ + "1.5b-q3_K_M", + "824\u202fMB" + ], + [ + "1.5b-q3_K_L", + "880\u202fMB" + ], + [ + "1.5b-q4_0", + "935\u202fMB" + ], + [ + "1.5b-q4_1", + "1.0\u202fGB" + ], + [ + "1.5b-q4_K_S", + "940\u202fMB" + ], + [ + "1.5b-q4_K_M", + "986\u202fMB" + ], + [ + "1.5b-q5_0", + "1.1\u202fGB" + ], + [ + "1.5b-q5_1", + "1.2\u202fGB" + ], + [ + "1.5b-q5_K_S", + "1.1\u202fGB" + ], + [ + "1.5b-q5_K_M", + "1.1\u202fGB" + ], + [ + "1.5b-q6_K", + "1.3\u202fGB" + ], + [ + "1.5b-q8_0", + "1.6\u202fGB" + ] + ], + "image": false, + "author": "Jina AI" + }, + "deepseek-v2.5": { + "url": "https://ollama.com/library/deepseek-v2.5", + "description": "An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.", + "tags": [ + [ + "latest", + "133\u202fGB" + ], + [ + "236b", + "133\u202fGB" + ], + [ + "236b-q4_0", + "133\u202fGB" + ], + [ + "236b-q4_1", + "148\u202fGB" + ], + [ + "236b-q5_0", + "162\u202fGB" + ], + [ + "236b-q5_1", + "177\u202fGB" + ], + [ + "236b-q8_0", + "251\u202fGB" + ] + ], + "image": false, + "author": "Deepseek AI" }, "paraphrase-multilingual": { "url": "https://ollama.com/library/paraphrase-multilingual", @@ -22122,5 +23654,81 @@ ], "image": false, "author": "Paraphrase Team" + }, + "bespoke-minicheck": { + "url": "https://ollama.com/library/bespoke-minicheck", + "description": "A state-of-the-art fact-checking model developed by Bespoke Labs.", + "tags": [ + [ + "latest", + "4.7\u202fGB" + ], + [ + "7b", + "4.7\u202fGB" + ], + [ + "7b-fp16", + "15\u202fGB" + ], + [ + "7b-q2_K", + "3.0\u202fGB" + ], + [ + "7b-q3_K_S", + "3.5\u202fGB" + ], + [ + "7b-q3_K_M", + "3.8\u202fGB" + ], + [ + "7b-q3_K_L", + "4.1\u202fGB" + ], + [ + "7b-q4_0", + "4.5\u202fGB" + ], + [ + "7b-q4_1", + "4.9\u202fGB" + ], + [ + "7b-q4_K_S", + "4.5\u202fGB" + ], + [ + "7b-q4_K_M", + "4.7\u202fGB" + ], + [ + "7b-q5_0", + "5.4\u202fGB" + ], + [ + "7b-q5_1", + "5.8\u202fGB" + ], + [ + "7b-q5_K_S", + "5.4\u202fGB" + ], + [ + "7b-q5_K_M", + "5.5\u202fGB" + ], + [ + "7b-q6_K", + "6.4\u202fGB" + ], + [ + "7b-q8_0", + "8.2\u202fGB" + ] + ], + "image": false, + "author": "Bespoke Labs" } } \ No newline at end of file diff --git a/src/available_models_descriptions.py b/src/available_models_descriptions.py index 504f754..b9b3f8b 100644 --- a/src/available_models_descriptions.py +++ b/src/available_models_descriptions.py @@ -1,11 +1,12 @@ descriptions = { 'llama3.1': _("Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes."), - 'gemma2': _("Google Gemma 2 is a high-performing and efficient model by now available in three sizes: 2B, 9B, and 27B."), + 'gemma2': _("Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B."), + 'qwen2.5': _("Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support."), + 'phi3.5': _("A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger sized models."), + 'nemotron-mini': _("A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling."), + 'mistral-small': _("Mistral Small is a lightweight model designed for cost-effective use in tasks like translation and summarization."), 'mistral-nemo': _("A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA."), - 'mistral-large': _("Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and support for dozens of languages."), - 'qwen2': _("Qwen2 is a new series of large language models from Alibaba group"), 'deepseek-coder-v2': _("An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks."), - 'phi3': _("Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft."), 'mistral': _("The 7B model released by Mistral AI, updated to version 0.3."), 'mixtral': _("A set of Mixture of Experts (MoE) model with open weights by Mistral AI in 8x7b and 8x22b parameter sizes."), 'codegemma': _("CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks like fill-in-the-middle code completion, code generation, natural language understanding, mathematical reasoning, and instruction following."), @@ -15,6 +16,8 @@ descriptions = { 'llama3': _("Meta Llama 3: The most capable openly available LLM to date"), 'gemma': _("Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1"), 'qwen': _("Qwen 1.5 is a series of large language models by Alibaba Cloud spanning from 0.5B to 110B parameters"), + 'qwen2': _("Qwen2 is a new series of large language models from Alibaba group"), + 'phi3': _("Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft."), 'llama2': _("Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters."), 'codellama': _("A large language model that can use text prompts to generate and discuss code."), 'nomic-embed-text': _("A high-performing open embedding model with a large token context window."), @@ -23,90 +26,98 @@ descriptions = { 'llama2-uncensored': _("Uncensored Llama 2 model by George Sung and Jarrad Hope."), 'deepseek-coder': _("DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens."), 'mxbai-embed-large': _("State-of-the-art large embedding model from mixedbread.ai"), - 'zephyr': _("Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants."), - 'dolphin-mistral': _("The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8."), 'starcoder2': _("StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters."), - 'orca-mini': _("A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware."), + 'dolphin-mistral': _("The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8."), + 'zephyr': _("Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants."), 'dolphin-llama3': _("Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills."), + 'orca-mini': _("A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware."), 'yi': _("Yi 1.5 is a high-performing, bilingual language model."), - 'mistral-openorca': _("Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset."), 'llava-llama3': _("A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks."), + 'mistral-openorca': _("Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset."), 'starcoder': _("StarCoder is a code generation model trained on 80+ programming languages."), - 'llama2-chinese': _("Llama 2 based model fine tuned to improve Chinese dialogue ability."), - 'vicuna': _("General use chat model based on Llama and Llama 2 with 2K to 16K context sizes."), 'tinyllama': _("The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens."), + 'vicuna': _("General use chat model based on Llama and Llama 2 with 2K to 16K context sizes."), 'codestral': _("Codestral is Mistral AI’s first-ever code model designed for code generation tasks."), + 'llama2-chinese': _("Llama 2 based model fine tuned to improve Chinese dialogue ability."), 'wizard-vicuna-uncensored': _("Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford."), + 'codegeex4': _("A versatile model for AI software development scenarios, including code completion."), 'nous-hermes2': _("The powerful family of models by Nous Research that excels at scientific discussion and coding tasks."), + 'granite-code': _("A family of open foundation models by IBM for Code Intelligence"), 'openchat': _("A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106."), 'aya': _("Aya 23, released by Cohere, is a new family of state-of-the-art, multilingual models that support 23 languages."), 'wizardlm2': _("State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases."), + 'codeqwen': _("CodeQwen1.5 is a large language model pretrained on a large amount of code data."), 'tinydolphin': _("An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama."), - 'granite-code': _("A family of open foundation models by IBM for Code Intelligence"), + 'all-minilm': _("Embedding models on very large sentence level datasets."), 'wizardcoder': _("State-of-the-art code generation model"), 'stable-code': _("Stable Code 3B is a coding model with instruct and code completion variants on par with models such as Code Llama 7B that are 2.5x larger."), 'openhermes': _("OpenHermes 2.5 is a 7B model fine-tuned by Teknium on Mistral with fully open datasets."), - 'all-minilm': _("Embedding models on very large sentence level datasets."), - 'codeqwen': _("CodeQwen1.5 is a large language model pretrained on a large amount of code data."), + 'bakllava': _("BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture."), 'stablelm2': _("Stable LM 2 is a state-of-the-art 1.6B and 12B parameter language model trained on multilingual data in English, Spanish, German, Italian, French, Portuguese, and Dutch."), + 'qwen2-math': _("Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o)."), 'wizard-math': _("Model focused on math and logic problems"), - 'neural-chat': _("A fine-tuned model based on Mistral with good coverage of domain and language."), 'llama3-gradient': _("This model extends LLama-3 8B's context length from 8k to over 1m tokens."), + 'neural-chat': _("A fine-tuned model based on Mistral with good coverage of domain and language."), + 'deepseek-llm': _("An advanced language model crafted with 2 trillion bilingual tokens."), 'phind-codellama': _("Code generation model based on Code Llama."), 'nous-hermes': _("General use models based on Llama and Llama 2 from Nous Research."), - 'dolphincoder': _("A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2."), - 'sqlcoder': _("SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks"), 'xwinlm': _("Conversational model based on Llama 2 that performs competitively on various benchmarks."), - 'deepseek-llm': _("An advanced language model crafted with 2 trillion bilingual tokens."), - 'yarn-llama2': _("An extension of Llama 2 that supports a context of up to 128k tokens."), + 'sqlcoder': _("SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks"), + 'dolphincoder': _("A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2."), 'llama3-chatqa': _("A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG)."), + 'yarn-llama2': _("An extension of Llama 2 that supports a context of up to 128k tokens."), + 'mistral-large': _("Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and support for dozens of languages."), 'wizardlm': _("General use model based on Llama 2."), - 'starling-lm': _("Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness."), - 'codegeex4': _("A versatile model for AI software development scenarios, including code completion."), - 'snowflake-arctic-embed': _("A suite of text embedding models by Snowflake, optimized for performance."), - 'orca2': _("Orca 2 is built by Microsoft research, and are a fine-tuned version of Meta's Llama 2 models. The model is designed to excel particularly in reasoning."), - 'solar': _("A compact, yet powerful 10.7B large language model designed for single-turn conversation."), - 'samantha-mistral': _("A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral."), - 'moondream': _("moondream2 is a small vision language model designed to run efficiently on edge devices."), 'smollm': _("🪐 A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset."), - 'stable-beluga': _("🪐 A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset."), - 'qwen2-math': _("Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o)."), - 'dolphin-phi': _("2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research."), + 'starling-lm': _("Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness."), + 'reflection': _("A high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct course."), + 'moondream': _("moondream2 is a small vision language model designed to run efficiently on edge devices."), + 'snowflake-arctic-embed': _("A suite of text embedding models by Snowflake, optimized for performance."), + 'samantha-mistral': _("A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral."), + 'solar': _("A compact, yet powerful 10.7B large language model designed for single-turn conversation."), + 'orca2': _("Orca 2 is built by Microsoft research, and are a fine-tuned version of Meta's Llama 2 models. The model is designed to excel particularly in reasoning."), 'deepseek-v2': _("A strong, economical, and efficient Mixture-of-Experts language model."), - 'bakllava': _("BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture."), + 'stable-beluga': _("Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy."), 'glm4': _("A strong multi-lingual general language model with competitive performance to Llama 3."), + 'dolphin-phi': _("2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research."), 'wizardlm-uncensored': _("Uncensored version of Wizard LM model"), - 'yarn-mistral': _("An extension of Mistral to support context windows of 64K or 128K."), - 'phi3.5': _("A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger sized models."), - 'medllama2': _("Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset."), - 'llama-pro': _("An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics."), 'llava-phi3': _("A new small LLaVA model fine-tuned from Phi 3 Mini."), + 'hermes3': _("Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research"), + 'yarn-mistral': _("An extension of Mistral to support context windows of 64K or 128K."), + 'llama-pro': _("An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics."), + 'medllama2': _("Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset."), + 'yi-coder': _("Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters."), + 'internlm2': _("InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability."), 'meditron': _("Open-source medical large language model adapted from Llama 2 to the medical domain."), - 'nous-hermes2-mixtral': _("The Nous Hermes 2 model from Nous Research, now trained over Mixtral."), 'nexusraven': _("Nexus Raven is a 13B instruction tuned model for function calling tasks."), + 'nous-hermes2-mixtral': _("The Nous Hermes 2 model from Nous Research, now trained over Mixtral."), 'codeup': _("Great code generation model based on Llama2."), 'everythinglm': _("Uncensored Llama2 based model with support for a 16K context window."), - 'hermes3': _("Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research"), - 'internlm2': _("InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability."), + 'llama3-groq-tool-use': _("A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling."), 'magicoder': _("🎩 Magicoder is a family of 7B parameter models trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets."), 'stablelm-zephyr': _("A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware."), 'codebooga': _("A high-performing code instruct model created by merging two existing code models."), 'mistrallite': _("MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts."), - 'llama3-groq-tool-use': _("A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling."), 'falcon2': _("Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens."), 'wizard-vicuna': _("Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj."), 'duckdb-nsql': _("7B parameter text-to-SQL model made by MotherDuck and Numbers Station."), + 'qwen2.5-coder': _("The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing."), 'megadolphin': _("MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself."), 'notux': _("A top-performing mixture of experts model, fine-tuned with high-quality data."), 'goliath': _("A language model created by combining two fine-tuned Llama 2 70B models into one."), 'open-orca-platypus2': _("Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation."), 'notus': _("A 7B chat model fine-tuned with high-quality data and based on Zephyr."), - 'dbrx': _("DBRX is an open, general-purpose LLM created by Databricks."), - 'mathstral': _("MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI."), 'bge-m3': _("BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity."), + 'mathstral': _("MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI."), + 'dbrx': _("DBRX is an open, general-purpose LLM created by Databricks."), + 'minicpm-v': _("A series of multimodal LLMs (MLLMs) designed for vision-language understanding."), + 'nuextract': _("A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, based on Phi-3."), 'alfred': _("A robust conversational model designed to be used for both chat and instruct use cases."), 'firefunction-v2': _("An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities."), - 'nuextract': _("A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, based on Phi-3."), + 'solar-pro': _("Solar Pro Preview: an advanced large language model (LLM) with 22 billion parameters designed to fit into a single GPU"), 'bge-large': _("Embedding model from BAAI mapping texts to vectors."), + 'reader-lm': _("A series of models that convert HTML content to Markdown content, which is useful for content conversion tasks."), + 'deepseek-v2.5': _("An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct."), 'paraphrase-multilingual': _("Sentence-transformers model that can be used for tasks like clustering or semantic search."), + 'bespoke-minicheck': _("A state-of-the-art fact-checking model developed by Bespoke Labs."), } \ No newline at end of file