From 6d8d3788a6b3957c8c50f6091f224c152265a6f1 Mon Sep 17 00:00:00 2001 From: jeffser Date: Mon, 29 Jul 2024 02:06:06 -0600 Subject: [PATCH] Added new models --- src/available_models.json | 7624 +++++++++++++------------- src/available_models_descriptions.py | 36 +- 2 files changed, 3913 insertions(+), 3747 deletions(-) diff --git a/src/available_models.json b/src/available_models.json index e8411ab..51d1b6f 100644 --- a/src/available_models.json +++ b/src/available_models.json @@ -1,4 +1,152 @@ { + "llama3.1": { + "url": "https://ollama.com/library/llama3.1", + "description": "Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.", + "tags": [ + [ + "latest", + "4.7GB" + ], + [ + "405b", + "231GB" + ], + [ + "70b", + "40GB" + ], + [ + "8b", + "4.7GB" + ], + [ + "70b-instruct-q2_k", + "26GB" + ], + [ + "70b-instruct-fp16", + "141GB" + ], + [ + "70b-instruct-q2_K", + "26GB" + ], + [ + "70b-instruct-q3_K_L", + "37GB" + ], + [ + "70b-instruct-q3_K_M", + "34GB" + ], + [ + "70b-instruct-q3_K_S", + "31GB" + ], + [ + "70b-instruct-q4_0", + "40GB" + ], + [ + "70b-instruct-q4_1", + "44GB" + ], + [ + "70b-instruct-q4_K_M", + "43GB" + ], + [ + "70b-instruct-q4_K_S", + "40GB" + ], + [ + "70b-instruct-q5_0", + "49GB" + ], + [ + "70b-instruct-q5_1", + "53GB" + ], + [ + "70b-instruct-q5_K_M", + "50GB" + ], + [ + "70b-instruct-q5_K_S", + "49GB" + ], + [ + "70b-instruct-q6_K", + "58GB" + ], + [ + "70b-instruct-q8_0", + "75GB" + ], + [ + "8b-instruct-fp16", + "16GB" + ], + [ + "8b-instruct-q2_K", + "3.2GB" + ], + [ + "8b-instruct-q3_K_L", + "4.3GB" + ], + [ + "8b-instruct-q3_K_M", + "4.0GB" + ], + [ + "8b-instruct-q3_K_S", + "3.7GB" + ], + [ + "8b-instruct-q4_0", + "4.7GB" + ], + [ + "8b-instruct-q4_1", + "5.1GB" + ], + [ + "8b-instruct-q4_K_M", + "4.9GB" + ], + [ + "8b-instruct-q4_K_S", + "4.7GB" + ], + [ + "8b-instruct-q5_0", + "5.6GB" + ], + [ + "8b-instruct-q5_1", + "6.1GB" + ], + [ + "8b-instruct-q5_K_M", + "5.7GB" + ], + [ + "8b-instruct-q5_K_S", + "5.6GB" + ], + [ + "8b-instruct-q6_K", + "6.6GB" + ], + [ + "8b-instruct-q8_0", + "8.5GB" + ] + ], + "image": false, + "author": "Meta" + }, "gemma2": { "url": "https://ollama.com/library/gemma2", "description": "Google Gemma 2 is now available in 2 sizes, 9B and 27B.", @@ -259,285 +407,157 @@ "image": false, "author": "Google DeepMind" }, - "llama3": { - "url": "https://ollama.com/library/llama3", - "description": "Meta Llama 3: The most capable openly available LLM to date", + "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", - "4.7GB" + "7.1GB" ], [ - "70b", - "40GB" + "12b", + "7.1GB" ], [ - "8b", - "4.7GB" + "12b-instruct-2407-fp16", + "25GB" ], [ - "instruct", - "4.7GB" + "12b-instruct-2407-q2_K", + "4.8GB" ], [ - "text", - "4.7GB" - ], - [ - "70b-instruct", - "40GB" - ], - [ - "70b-instruct-fp16", - "141GB" - ], - [ - "70b-instruct-q2_K", - "26GB" - ], - [ - "70b-instruct-q3_K_L", - "37GB" - ], - [ - "70b-instruct-q3_K_M", - "34GB" - ], - [ - "70b-instruct-q3_K_S", - "31GB" - ], - [ - "70b-instruct-q4_0", - "40GB" - ], - [ - "70b-instruct-q4_1", - "44GB" - ], - [ - "70b-instruct-q4_K_M", - "43GB" - ], - [ - "70b-instruct-q4_K_S", - "40GB" - ], - [ - "70b-instruct-q5_0", - "49GB" - ], - [ - "70b-instruct-q5_1", - "53GB" - ], - [ - "70b-instruct-q5_K_M", - "50GB" - ], - [ - "70b-instruct-q5_K_S", - "49GB" - ], - [ - "70b-instruct-q6_K", - "58GB" - ], - [ - "70b-instruct-q8_0", - "75GB" - ], - [ - "70b-text", - "40GB" - ], - [ - "70b-text-fp16", - "141GB" - ], - [ - "70b-text-q2_K", - "26GB" - ], - [ - "70b-text-q3_K_L", - "37GB" - ], - [ - "70b-text-q3_K_M", - "34GB" - ], - [ - "70b-text-q3_K_S", - "31GB" - ], - [ - "70b-text-q4_0", - "40GB" - ], - [ - "70b-text-q4_1", - "44GB" - ], - [ - "70b-text-q4_K_M", - "43GB" - ], - [ - "70b-text-q4_K_S", - "40GB" - ], - [ - "70b-text-q5_0", - "49GB" - ], - [ - "70b-text-q5_1", - "53GB" - ], - [ - "70b-text-q5_K_M", - "50GB" - ], - [ - "70b-text-q5_K_S", - "49GB" - ], - [ - "70b-text-q6_K", - "58GB" - ], - [ - "70b-text-q8_0", - "75GB" - ], - [ - "8b-instruct-fp16", - "16GB" - ], - [ - "8b-instruct-q2_K", - "3.2GB" - ], - [ - "8b-instruct-q3_K_L", - "4.3GB" - ], - [ - "8b-instruct-q3_K_M", - "4.0GB" - ], - [ - "8b-instruct-q3_K_S", - "3.7GB" - ], - [ - "8b-instruct-q4_0", - "4.7GB" - ], - [ - "8b-instruct-q4_1", - "5.1GB" - ], - [ - "8b-instruct-q4_K_M", - "4.9GB" - ], - [ - "8b-instruct-q4_K_S", - "4.7GB" - ], - [ - "8b-instruct-q5_0", - "5.6GB" - ], - [ - "8b-instruct-q5_1", - "6.1GB" - ], - [ - "8b-instruct-q5_K_M", - "5.7GB" - ], - [ - "8b-instruct-q5_K_S", - "5.6GB" - ], - [ - "8b-instruct-q6_K", + "12b-instruct-2407-q3_K_L", "6.6GB" ], [ - "8b-instruct-q8_0", - "8.5GB" - ], - [ - "8b-text", - "4.7GB" - ], - [ - "8b-text-fp16", - "16GB" - ], - [ - "8b-text-q2_K", - "3.2GB" - ], - [ - "8b-text-q3_K_L", - "4.3GB" - ], - [ - "8b-text-q3_K_M", - "4.0GB" - ], - [ - "8b-text-q3_K_S", - "3.7GB" - ], - [ - "8b-text-q4_0", - "4.7GB" - ], - [ - "8b-text-q4_1", - "5.1GB" - ], - [ - "8b-text-q4_K_M", - "4.9GB" - ], - [ - "8b-text-q4_K_S", - "4.7GB" - ], - [ - "8b-text-q5_0", - "5.6GB" - ], - [ - "8b-text-q5_1", + "12b-instruct-2407-q3_K_M", "6.1GB" ], [ - "8b-text-q5_K_M", - "5.7GB" + "12b-instruct-2407-q3_K_S", + "5.5GB" ], [ - "8b-text-q5_K_S", - "5.6GB" + "12b-instruct-2407-q4_0", + "7.1GB" ], [ - "8b-text-q6_K", - "6.6GB" + "12b-instruct-2407-q4_1", + "7.8GB" ], [ - "8b-text-q8_0", + "12b-instruct-2407-q4_K_M", + "7.5GB" + ], + [ + "12b-instruct-2407-q4_K_S", + "7.1GB" + ], + [ + "12b-instruct-2407-q5_0", "8.5GB" + ], + [ + "12b-instruct-2407-q5_1", + "9.2GB" + ], + [ + "12b-instruct-2407-q5_K_M", + "8.7GB" + ], + [ + "12b-instruct-2407-q5_K_S", + "8.5GB" + ], + [ + "12b-instruct-2407-q6_K", + "10GB" + ], + [ + "12b-instruct-2407-q8_0", + "13GB" ] ], "image": false, - "author": "Meta" + "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", + "69GB" + ], + [ + "123b", + "69GB" + ], + [ + "123b-instruct-2407-fp16", + "245GB" + ], + [ + "123b-instruct-2407-q2_K", + "45GB" + ], + [ + "123b-instruct-2407-q3_K_L", + "65GB" + ], + [ + "123b-instruct-2407-q3_K_M", + "59GB" + ], + [ + "123b-instruct-2407-q3_K_S", + "53GB" + ], + [ + "123b-instruct-2407-q4_0", + "69GB" + ], + [ + "123b-instruct-2407-q4_1", + "77GB" + ], + [ + "123b-instruct-2407-q4_K_M", + "73GB" + ], + [ + "123b-instruct-2407-q4_K_S", + "70GB" + ], + [ + "123b-instruct-2407-q5_0", + "84GB" + ], + [ + "123b-instruct-2407-q5_1", + "92GB" + ], + [ + "123b-instruct-2407-q5_K_M", + "86GB" + ], + [ + "123b-instruct-2407-q5_K_S", + "84GB" + ], + [ + "123b-instruct-2407-q6_K", + "101GB" + ], + [ + "123b-instruct-2407-q8_0", + "130GB" + ] + ], + "image": false, + "author": "Mistral AI" }, "qwen2": { "url": "https://ollama.com/library/qwen2", @@ -1176,11 +1196,11 @@ "7.9GB" ], [ - "14b-medium-4k-instruct-f16", + "14b-medium-128k-instruct-f16", "28GB" ], [ - "14b-medium-128k-instruct-f16", + "14b-medium-4k-instruct-f16", "28GB" ], [ @@ -1443,154 +1463,6 @@ "image": false, "author": "Microsoft" }, - "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", - "4.8GB" - ], - [ - "35b", - "20GB" - ], - [ - "8b", - "4.8GB" - ], - [ - "35b-23-f16", - "70GB" - ], - [ - "35b-23", - "20GB" - ], - [ - "35b-23-q2_K", - "14GB" - ], - [ - "35b-23-q3_K_L", - "19GB" - ], - [ - "35b-23-q3_K_M", - "18GB" - ], - [ - "35b-23-q3_K_S", - "16GB" - ], - [ - "35b-23-q4_0", - "20GB" - ], - [ - "35b-23-q4_1", - "22GB" - ], - [ - "35b-23-q4_K_M", - "22GB" - ], - [ - "35b-23-q4_K_S", - "20GB" - ], - [ - "35b-23-q5_0", - "24GB" - ], - [ - "35b-23-q5_1", - "26GB" - ], - [ - "35b-23-q5_K_M", - "25GB" - ], - [ - "35b-23-q5_K_S", - "24GB" - ], - [ - "35b-23-q6_K", - "29GB" - ], - [ - "35b-23-q8_0", - "37GB" - ], - [ - "8b-23", - "4.8GB" - ], - [ - "8b-23-f16", - "16GB" - ], - [ - "8b-23-q2_K", - "3.4GB" - ], - [ - "8b-23-q3_K_L", - "4.5GB" - ], - [ - "8b-23-q3_K_M", - "4.2GB" - ], - [ - "8b-23-q3_K_S", - "3.9GB" - ], - [ - "8b-23-q4_0", - "4.8GB" - ], - [ - "8b-23-q4_1", - "5.2GB" - ], - [ - "8b-23-q4_K_M", - "5.1GB" - ], - [ - "8b-23-q4_K_S", - "4.8GB" - ], - [ - "8b-23-q5_0", - "5.7GB" - ], - [ - "8b-23-q5_1", - "6.1GB" - ], - [ - "8b-23-q5_K_M", - "5.8GB" - ], - [ - "8b-23-q5_K_S", - "5.7GB" - ], - [ - "8b-23-q6_K", - "6.6GB" - ], - [ - "8b-23-q8_0", - "8.5GB" - ] - ], - "image": false, - "author": "Cohere" - }, "mistral": { "url": "https://ollama.com/library/mistral", "description": "The 7B model released by Mistral AI, updated to version 0.3.", @@ -1716,32 +1588,60 @@ "4.6GB" ], [ - "7b-instruct-v0.3-q4_K_M", - "4.4GB" + "7b-instruct-q4_0", + "4.1GB" + ], + [ + "7b-instruct-v0.3-q5_K_M", + "5.1GB" + ], + [ + "7b-instruct-v0.3-q8_0", + "7.7GB" ], [ "7b-instruct-v0.3-q4_K_S", "4.1GB" ], + [ + "7b-instruct-q3_K_M", + "3.5GB" + ], + [ + "7b-instruct-fp16", + "14GB" + ], + [ + "7b-instruct-q3_K_L", + "3.8GB" + ], [ "7b-instruct-v0.3-q5_0", "5.0GB" ], + [ + "7b-instruct-q2_K", + "3.1GB" + ], + [ + "7b-instruct-q3_K_S", + "3.2GB" + ], + [ + "7b-instruct-v0.3-q6_K", + "5.9GB" + ], + [ + "7b-instruct-v0.3-q5_K_S", + "5.0GB" + ], [ "7b-instruct-v0.3-q5_1", "5.4GB" ], [ - "7b-instruct-v0.3-q5_K_M", - "5.1GB" - ], - [ - "7b-instruct-v0.3-q5_K_S", - "5.0GB" - ], - [ - "7b-instruct-v0.3-q6_K", - "5.9GB" + "7b-instruct-v0.3-q4_K_M", + "4.4GB" ], [ "7b-instruct-q6_K", @@ -1752,47 +1652,7 @@ "5.0GB" ], [ - "7b-instruct-q5_1", - "5.4GB" - ], - [ - "7b-instruct-q4_1", - "4.6GB" - ], - [ - "7b-instruct-fp16", - "14GB" - ], - [ - "7b-instruct-q3_K_S", - "3.2GB" - ], - [ - "7b-instruct-q3_K_L", - "3.8GB" - ], - [ - "7b-instruct-q4_K_M", - "4.4GB" - ], - [ - "7b-instruct-v0.3-q8_0", - "7.7GB" - ], - [ - "7b-instruct-q2_K", - "3.1GB" - ], - [ - "7b-instruct-q3_K_M", - "3.5GB" - ], - [ - "7b-instruct-q5_0", - "5.0GB" - ], - [ - "7b-instruct-q4_0", + "7b-instruct-q4_K_S", "4.1GB" ], [ @@ -1800,8 +1660,20 @@ "5.1GB" ], [ - "7b-instruct-q4_K_S", - "4.1GB" + "7b-instruct-q4_1", + "4.6GB" + ], + [ + "7b-instruct-q5_0", + "5.0GB" + ], + [ + "7b-instruct-q4_K_M", + "4.4GB" + ], + [ + "7b-instruct-q5_1", + "5.4GB" ], [ "7b-instruct-q8_0", @@ -1827,30 +1699,22 @@ "7b-text-q3_K_M", "3.5GB" ], + [ + "7b-text-v0.2-q3_K_M", + "3.5GB" + ], + [ + "7b-text-q8_0", + "7.7GB" + ], + [ + "7b-text-q5_K_S", + "5.0GB" + ], [ "7b-text-q3_K_S", "3.2GB" ], - [ - "7b-text-q4_0", - "4.1GB" - ], - [ - "7b-text-q4_1", - "4.6GB" - ], - [ - "7b-text-q4_K_M", - "4.4GB" - ], - [ - "7b-text-v0.2-q3_K_S", - "3.2GB" - ], - [ - "7b-text-v0.2-fp16", - "14GB" - ], [ "7b-text-q5_0", "5.0GB" @@ -1860,36 +1724,44 @@ "5.1GB" ], [ - "7b-text-q5_1", - "5.4GB" + "7b-text-q4_K_M", + "4.4GB" ], [ - "7b-text-q4_K_S", - "4.1GB" - ], - [ - "7b-text-v0.2-q2_K", - "2.7GB" - ], - [ - "7b-text-v0.2-q3_K_M", - "3.5GB" + "7b-text-q4_1", + "4.6GB" ], [ "7b-text-v0.2-q3_K_L", "3.8GB" ], - [ - "7b-text-q8_0", - "7.7GB" - ], [ "7b-text-q6_K", "5.9GB" ], [ - "7b-text-q5_K_S", - "5.0GB" + "7b-text-q4_0", + "4.1GB" + ], + [ + "7b-text-q5_1", + "5.4GB" + ], + [ + "7b-text-v0.2-q2_K", + "2.7GB" + ], + [ + "7b-text-v0.2-fp16", + "14GB" + ], + [ + "7b-text-q4_K_S", + "4.1GB" + ], + [ + "7b-text-v0.2-q3_K_S", + "3.2GB" ], [ "7b-text-v0.2-q4_0", @@ -1943,14 +1815,14 @@ "latest", "26GB" ], - [ - "8x22b", - "80GB" - ], [ "8x7b", "26GB" ], + [ + "8x22b", + "80GB" + ], [ "instruct", "26GB" @@ -2324,63 +2196,55 @@ "4.7GB" ], [ - "7b-instruct-v1.1-q3_K_M", - "4.4GB" - ], - [ - "7b-instruct-v1.1-q3_K_S", + "7b-instruct-q3_K_S", "4.0GB" ], - [ - "7b-instruct-v1.1-q4_0", - "5.0GB" - ], - [ - "7b-instruct-v1.1-q4_1", - "5.5GB" - ], - [ - "7b-instruct-v1.1-q4_K_M", - "5.3GB" - ], - [ - "7b-instruct-v1.1-q4_K_S", - "5.0GB" - ], - [ - "7b-instruct-v1.1-q5_0", - "6.0GB" - ], - [ - "7b-instruct-v1.1-q5_1", - "6.5GB" - ], - [ - "7b-instruct-v1.1-q5_K_M", - "6.1GB" - ], - [ - "7b-instruct-v1.1-q5_K_S", - "6.0GB" - ], [ "7b-instruct-v1.1-q6_K", "7.0GB" ], [ - "7b-instruct-q4_K_S", + "7b-instruct-v1.1-q5_K_M", + "6.1GB" + ], + [ + "7b-instruct-v1.1-q8_0", + "9.1GB" + ], + [ + "7b-instruct-v1.1-q4_0", "5.0GB" ], [ - "7b-instruct-q4_0", + "7b-instruct-v1.1-q5_K_S", + "6.0GB" + ], + [ + "7b-instruct-fp16", + "17GB" + ], + [ + "7b-instruct-v1.1-q5_1", + "6.5GB" + ], + [ + "7b-instruct-v1.1-q4_1", + "5.5GB" + ], + [ + "7b-instruct-v1.1-q5_0", + "6.0GB" + ], + [ + "7b-instruct-v1.1-q3_K_M", + "4.4GB" + ], + [ + "7b-instruct-v1.1-q4_K_S", "5.0GB" ], [ - "7b-instruct-q3_K_L", - "4.7GB" - ], - [ - "7b-instruct-q4_K_M", + "7b-instruct-v1.1-q4_K_M", "5.3GB" ], [ @@ -2388,25 +2252,33 @@ "4.4GB" ], [ - "7b-instruct-fp16", - "17GB" + "7b-instruct-v1.1-q3_K_S", + "4.0GB" ], [ "7b-instruct-q2_K", "3.5GB" ], [ - "7b-instruct-q3_K_S", - "4.0GB" + "7b-instruct-q3_K_L", + "4.7GB" ], [ - "7b-instruct-v1.1-q8_0", - "9.1GB" + "7b-instruct-q4_0", + "5.0GB" ], [ "7b-instruct-q4_1", "5.5GB" ], + [ + "7b-instruct-q4_K_M", + "5.3GB" + ], + [ + "7b-instruct-q4_K_S", + "5.0GB" + ], [ "7b-instruct-q5_0", "6.0GB" @@ -2439,13 +2311,61 @@ "2b-code", "1.6GB" ], + [ + "2b-code-fp16", + "5.0GB" + ], + [ + "2b-code-q2_K", + "1.2GB" + ], + [ + "2b-code-q3_K_L", + "1.5GB" + ], + [ + "2b-code-q3_K_M", + "1.4GB" + ], + [ + "2b-code-q3_K_S", + "1.3GB" + ], + [ + "2b-code-q4_0", + "1.6GB" + ], + [ + "2b-code-q4_1", + "1.7GB" + ], + [ + "2b-code-q4_K_M", + "1.6GB" + ], + [ + "2b-code-q4_K_S", + "1.6GB" + ], + [ + "2b-code-q5_0", + "1.8GB" + ], + [ + "2b-code-v1.1-q4_1", + "1.7GB" + ], [ "2b-code-v1.1-fp16", "5.0GB" ], [ - "2b-code-v1.1-q2_K", - "1.2GB" + "2b-code-v1.1-q3_K_S", + "1.3GB" + ], + [ + "2b-code-q5_1", + "1.9GB" ], [ "2b-code-v1.1-q3_K_L", @@ -2456,16 +2376,28 @@ "1.4GB" ], [ - "2b-code-v1.1-q3_K_S", - "1.3GB" + "2b-code-q5_K_S", + "1.8GB" + ], + [ + "2b-code-q8_0", + "2.7GB" ], [ "2b-code-v1.1-q4_0", "1.6GB" ], [ - "2b-code-v1.1-q4_1", - "1.7GB" + "2b-code-v1.1-q2_K", + "1.2GB" + ], + [ + "2b-code-q6_K", + "2.1GB" + ], + [ + "2b-code-q5_K_M", + "1.8GB" ], [ "2b-code-v1.1-q4_K_M", @@ -2488,77 +2420,17 @@ "1.8GB" ], [ - "2b-code-q4_1", - "1.7GB" - ], - [ - "2b-code-q3_K_S", - "1.3GB" - ], - [ - "2b-code-fp16", - "5.0GB" + "2b-code-v1.1-q5_K_S", + "1.8GB" ], [ "2b-code-v1.1-q6_K", "2.1GB" ], - [ - "2b-code-q2_K", - "1.2GB" - ], - [ - "2b-code-q3_K_L", - "1.5GB" - ], - [ - "2b-code-q3_K_M", - "1.4GB" - ], [ "2b-code-v1.1-q8_0", "2.7GB" ], - [ - "2b-code-v1.1-q5_K_S", - "1.8GB" - ], - [ - "2b-code-q4_0", - "1.6GB" - ], - [ - "2b-code-q4_K_M", - "1.6GB" - ], - [ - "2b-code-q4_K_S", - "1.6GB" - ], - [ - "2b-code-q5_0", - "1.8GB" - ], - [ - "2b-code-q5_1", - "1.9GB" - ], - [ - "2b-code-q5_K_M", - "1.8GB" - ], - [ - "2b-code-q5_K_S", - "1.8GB" - ], - [ - "2b-code-q6_K", - "2.1GB" - ], - [ - "2b-code-q8_0", - "2.7GB" - ], [ "2b-v1.1", "1.6GB" @@ -3075,6 +2947,286 @@ "image": true, "author": "Haotian Liu" }, + "llama3": { + "url": "https://ollama.com/library/llama3", + "description": "Meta Llama 3: The most capable openly available LLM to date", + "tags": [ + [ + "latest", + "4.7GB" + ], + [ + "70b", + "40GB" + ], + [ + "8b", + "4.7GB" + ], + [ + "instruct", + "4.7GB" + ], + [ + "text", + "4.7GB" + ], + [ + "70b-instruct", + "40GB" + ], + [ + "70b-instruct-fp16", + "141GB" + ], + [ + "70b-instruct-q2_K", + "26GB" + ], + [ + "70b-instruct-q3_K_L", + "37GB" + ], + [ + "70b-instruct-q3_K_M", + "34GB" + ], + [ + "70b-instruct-q3_K_S", + "31GB" + ], + [ + "70b-instruct-q4_0", + "40GB" + ], + [ + "70b-instruct-q4_1", + "44GB" + ], + [ + "70b-instruct-q4_K_M", + "43GB" + ], + [ + "70b-instruct-q4_K_S", + "40GB" + ], + [ + "70b-instruct-q5_0", + "49GB" + ], + [ + "70b-instruct-q5_1", + "53GB" + ], + [ + "70b-instruct-q5_K_M", + "50GB" + ], + [ + "70b-instruct-q5_K_S", + "49GB" + ], + [ + "70b-instruct-q6_K", + "58GB" + ], + [ + "70b-instruct-q8_0", + "75GB" + ], + [ + "70b-text", + "40GB" + ], + [ + "70b-text-fp16", + "141GB" + ], + [ + "70b-text-q2_K", + "26GB" + ], + [ + "70b-text-q3_K_L", + "37GB" + ], + [ + "70b-text-q3_K_M", + "34GB" + ], + [ + "70b-text-q3_K_S", + "31GB" + ], + [ + "70b-text-q4_0", + "40GB" + ], + [ + "70b-text-q4_1", + "44GB" + ], + [ + "70b-text-q4_K_M", + "43GB" + ], + [ + "70b-text-q4_K_S", + "40GB" + ], + [ + "70b-text-q5_0", + "49GB" + ], + [ + "70b-text-q5_1", + "53GB" + ], + [ + "70b-text-q5_K_M", + "50GB" + ], + [ + "70b-text-q5_K_S", + "49GB" + ], + [ + "70b-text-q6_K", + "58GB" + ], + [ + "70b-text-q8_0", + "75GB" + ], + [ + "8b-instruct-fp16", + "16GB" + ], + [ + "8b-instruct-q2_K", + "3.2GB" + ], + [ + "8b-instruct-q3_K_L", + "4.3GB" + ], + [ + "8b-instruct-q3_K_M", + "4.0GB" + ], + [ + "8b-instruct-q3_K_S", + "3.7GB" + ], + [ + "8b-instruct-q4_0", + "4.7GB" + ], + [ + "8b-instruct-q4_1", + "5.1GB" + ], + [ + "8b-instruct-q4_K_M", + "4.9GB" + ], + [ + "8b-instruct-q4_K_S", + "4.7GB" + ], + [ + "8b-instruct-q5_0", + "5.6GB" + ], + [ + "8b-instruct-q5_1", + "6.1GB" + ], + [ + "8b-instruct-q5_K_M", + "5.7GB" + ], + [ + "8b-instruct-q5_K_S", + "5.6GB" + ], + [ + "8b-instruct-q6_K", + "6.6GB" + ], + [ + "8b-instruct-q8_0", + "8.5GB" + ], + [ + "8b-text", + "4.7GB" + ], + [ + "8b-text-fp16", + "16GB" + ], + [ + "8b-text-q2_K", + "3.2GB" + ], + [ + "8b-text-q3_K_L", + "4.3GB" + ], + [ + "8b-text-q3_K_M", + "4.0GB" + ], + [ + "8b-text-q3_K_S", + "3.7GB" + ], + [ + "8b-text-q4_0", + "4.7GB" + ], + [ + "8b-text-q4_1", + "5.1GB" + ], + [ + "8b-text-q4_K_M", + "4.9GB" + ], + [ + "8b-text-q4_K_S", + "4.7GB" + ], + [ + "8b-text-q5_0", + "5.6GB" + ], + [ + "8b-text-q5_1", + "6.1GB" + ], + [ + "8b-text-q5_K_M", + "5.7GB" + ], + [ + "8b-text-q5_K_S", + "5.6GB" + ], + [ + "8b-text-q6_K", + "6.6GB" + ], + [ + "8b-text-q8_0", + "8.5GB" + ] + ], + "image": false, + "author": "Meta" + }, "gemma": { "url": "https://ollama.com/library/gemma", "description": "Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1", @@ -3132,64 +3284,68 @@ "5.0GB" ], [ - "7b-instruct-q8_0", - "9.1GB" - ], - [ - "7b-instruct-v1.1-q5_1", - "6.5GB" - ], - [ - "7b-instruct-q3_K_L", - "4.9GB" - ], - [ - "7b-instruct-fp16", - "17GB" - ], - [ - "7b-instruct-q5_0", - "6.2GB" - ], - [ - "7b-instruct-v1.1-q6_K", - "7.0GB" + "7b-instruct-v1.1-q4_1", + "5.5GB" ], [ "7b-instruct-v1.1-q4_K_M", "5.3GB" ], - [ - "7b-instruct-q3_K_S", - "4.2GB" - ], - [ - "7b-instruct-q4_1", - "5.7GB" - ], [ "7b-instruct-v1.1-q4_K_S", "5.0GB" ], [ - "7b-instruct-q3_K_M", - "4.6GB" + "7b-instruct-v1.1-q5_0", + "6.0GB" ], [ - "7b-instruct-q6_K", - "7.2GB" + "7b-instruct-v1.1-q5_1", + "6.5GB" ], [ - "7b-instruct-v1.1-q4_1", - "5.5GB" + "7b-instruct-v1.1-q5_K_M", + "6.1GB" + ], + [ + "7b-instruct-v1.1-q5_K_S", + "6.0GB" + ], + [ + "7b-instruct-v1.1-q6_K", + "7.0GB" + ], + [ + "7b-instruct-q4_0", + "5.2GB" ], [ "7b-instruct-q2_K", "3.7GB" ], [ - "7b-instruct-v1.1-q5_K_S", - "6.0GB" + "7b-instruct-q3_K_S", + "4.2GB" + ], + [ + "7b-instruct-fp16", + "17GB" + ], + [ + "7b-instruct-q3_K_L", + "4.9GB" + ], + [ + "7b-instruct-v1.1-q8_0", + "9.1GB" + ], + [ + "7b-instruct-q3_K_M", + "4.6GB" + ], + [ + "7b-instruct-q4_1", + "5.7GB" ], [ "7b-instruct-q4_K_M", @@ -3199,33 +3355,29 @@ "7b-instruct-q4_K_S", "5.2GB" ], + [ + "7b-instruct-q5_0", + "6.2GB" + ], [ "7b-instruct-q5_1", "6.7GB" ], [ - "7b-instruct-v1.1-q8_0", - "9.1GB" - ], - [ - "7b-instruct-v1.1-q5_K_M", - "6.1GB" - ], - [ - "7b-instruct-q4_0", - "5.2GB" - ], - [ - "7b-instruct-v1.1-q5_0", - "6.0GB" + "7b-instruct-q5_K_M", + "6.3GB" ], [ "7b-instruct-q5_K_S", "6.2GB" ], [ - "7b-instruct-q5_K_M", - "6.3GB" + "7b-instruct-q6_K", + "7.2GB" + ], + [ + "7b-instruct-q8_0", + "9.1GB" ], [ "7b-text", @@ -3300,43 +3452,67 @@ "1.6GB" ], [ - "2b-instruct-v1.1-fp16", - "5.0GB" + "2b-instruct-fp16", + "4.5GB" ], [ - "2b-instruct-v1.1-q2_K", - "1.2GB" - ], - [ - "2b-instruct-v1.1-q3_K_L", - "1.5GB" - ], - [ - "2b-instruct-v1.1-q3_K_M", - "1.4GB" - ], - [ - "2b-instruct-v1.1-q3_K_S", + "2b-instruct-q2_K", "1.3GB" ], [ - "2b-instruct-v1.1-q4_0", + "2b-instruct-q3_K_L", "1.6GB" ], [ - "2b-instruct-v1.1-q4_1", + "2b-instruct-q3_K_M", + "1.5GB" + ], + [ + "2b-instruct-q3_K_S", + "1.4GB" + ], + [ + "2b-instruct-q4_0", "1.7GB" ], [ - "2b-instruct-v1.1-q4_K_M", - "1.6GB" + "2b-instruct-q4_1", + "1.8GB" ], [ - "2b-instruct-v1.1-q4_K_S", - "1.6GB" + "2b-instruct-q4_K_M", + "1.8GB" ], [ - "2b-instruct-v1.1-q5_0", + "2b-instruct-q4_K_S", + "1.7GB" + ], + [ + "2b-instruct-q5_0", + "1.9GB" + ], + [ + "2b-instruct-q5_1", + "2.1GB" + ], + [ + "2b-instruct-q5_K_M", + "2.0GB" + ], + [ + "2b-instruct-q5_K_S", + "1.9GB" + ], + [ + "2b-instruct-q6_K", + "2.2GB" + ], + [ + "2b-instruct-q8_0", + "2.7GB" + ], + [ + "2b-instruct-v1.1-q5_K_M", "1.8GB" ], [ @@ -3344,9 +3520,45 @@ "1.9GB" ], [ - "2b-instruct-v1.1-q5_K_M", + "2b-instruct-v1.1-q2_K", + "1.2GB" + ], + [ + "2b-instruct-v1.1-q3_K_M", + "1.4GB" + ], + [ + "2b-instruct-v1.1-q4_0", + "1.6GB" + ], + [ + "2b-instruct-v1.1-q3_K_L", + "1.5GB" + ], + [ + "2b-instruct-v1.1-q3_K_S", + "1.3GB" + ], + [ + "2b-instruct-v1.1-q4_K_S", + "1.6GB" + ], + [ + "2b-instruct-v1.1-fp16", + "5.0GB" + ], + [ + "2b-instruct-v1.1-q4_K_M", + "1.6GB" + ], + [ + "2b-instruct-v1.1-q5_0", "1.8GB" ], + [ + "2b-instruct-v1.1-q4_1", + "1.7GB" + ], [ "2b-instruct-v1.1-q5_K_S", "1.8GB" @@ -3359,66 +3571,6 @@ "2b-instruct-v1.1-q8_0", "2.7GB" ], - [ - "2b-instruct-q6_K", - "2.2GB" - ], - [ - "2b-instruct-q5_K_S", - "1.9GB" - ], - [ - "2b-instruct-q5_1", - "2.1GB" - ], - [ - "2b-instruct-q4_K_S", - "1.7GB" - ], - [ - "2b-instruct-q3_K_L", - "1.6GB" - ], - [ - "2b-instruct-q5_0", - "1.9GB" - ], - [ - "2b-instruct-q4_1", - "1.8GB" - ], - [ - "2b-instruct-q5_K_M", - "2.0GB" - ], - [ - "2b-instruct-q2_K", - "1.3GB" - ], - [ - "2b-instruct-fp16", - "4.5GB" - ], - [ - "2b-instruct-q4_0", - "1.7GB" - ], - [ - "2b-instruct-q4_K_M", - "1.8GB" - ], - [ - "2b-instruct-q3_K_M", - "1.5GB" - ], - [ - "2b-instruct-q3_K_S", - "1.4GB" - ], - [ - "2b-instruct-q8_0", - "2.7GB" - ], [ "2b-text", "1.7GB" @@ -3696,23 +3848,7 @@ "42GB" ], [ - "72b-chat-q5_1", - "54GB" - ], - [ - "72b-chat-v1.5-q8_0", - "77GB" - ], - [ - "72b-chat-q3_K_S", - "32GB" - ], - [ - "72b-chat-q3_K_L", - "39GB" - ], - [ - "72b-chat-q4_1", + "72b-chat-q4_K_M", "45GB" ], [ @@ -3728,28 +3864,12 @@ "41GB" ], [ - "72b-chat-v1.5-q5_1", - "54GB" + "72b-chat-q3_K_S", + "32GB" ], [ - "72b-chat-v1.5-q5_K_M", - "51GB" - ], - [ - "72b-chat-q5_0", - "50GB" - ], - [ - "72b-chat-q2_K", - "27GB" - ], - [ - "72b-chat-q4_K_M", - "45GB" - ], - [ - "72b-chat-fp16", - "145GB" + "72b-chat-q3_K_L", + "39GB" ], [ "72b-chat-q3_K_M", @@ -3759,10 +3879,42 @@ "72b-chat-v1.5-q5_0", "50GB" ], + [ + "72b-chat-fp16", + "145GB" + ], + [ + "72b-chat-v1.5-q5_1", + "54GB" + ], + [ + "72b-chat-q2_K", + "27GB" + ], + [ + "72b-chat-v1.5-q8_0", + "77GB" + ], + [ + "72b-chat-q4_1", + "45GB" + ], + [ + "72b-chat-v1.5-q5_K_M", + "51GB" + ], [ "72b-chat-q4_K_S", "41GB" ], + [ + "72b-chat-q5_0", + "50GB" + ], + [ + "72b-chat-q5_1", + "54GB" + ], [ "72b-chat-q5_K_M", "53GB" @@ -3784,80 +3936,16 @@ "63GB" ], [ - "72b-text-v1.5-fp16", + "72b-text-fp16", "145GB" ], - [ - "72b-text-v1.5-q2_K", - "28GB" - ], - [ - "72b-text-v1.5-q3_K_L", - "38GB" - ], - [ - "72b-text-v1.5-q3_K_M", - "36GB" - ], - [ - "72b-text-v1.5-q3_K_S", - "33GB" - ], - [ - "72b-text-v1.5-q4_0", - "41GB" - ], - [ - "72b-text-v1.5-q4_1", - "45GB" - ], - [ - "72b-text-v1.5-q4_K_M", - "44GB" - ], - [ - "72b-text-v1.5-q4_K_S", - "42GB" - ], - [ - "72b-text-v1.5-q5_0", - "50GB" - ], - [ - "72b-text-v1.5-q5_1", - "54GB" - ], - [ - "72b-text-v1.5-q5_K_M", - "51GB" - ], - [ - "72b-text-v1.5-q5_K_S", - "50GB" - ], - [ - "72b-text-q5_0", - "50GB" - ], - [ - "72b-text-q3_K_L", - "39GB" - ], [ "72b-text-q2_K", "27GB" ], [ - "72b-text-q4_K_S", - "41GB" - ], - [ - "72b-text-v1.5-q6_K", - "59GB" - ], - [ - "72b-text-q4_0", - "41GB" + "72b-text-q3_K_L", + "39GB" ], [ "72b-text-q3_K_M", @@ -3868,12 +3956,8 @@ "32GB" ], [ - "72b-text-v1.5-q8_0", - "77GB" - ], - [ - "72b-text-fp16", - "145GB" + "72b-text-q4_0", + "41GB" ], [ "72b-text-q4_1", @@ -3883,6 +3967,14 @@ "72b-text-q4_K_M", "45GB" ], + [ + "72b-text-q4_K_S", + "41GB" + ], + [ + "72b-text-q5_0", + "50GB" + ], [ "72b-text-q5_1", "54GB" @@ -3895,14 +3987,74 @@ "72b-text-q5_K_S", "50GB" ], + [ + "72b-text-v1.5-q5_1", + "54GB" + ], + [ + "72b-text-v1.5-q4_K_M", + "44GB" + ], + [ + "72b-text-v1.5-q5_0", + "50GB" + ], [ "72b-text-q6_K", "59GB" ], + [ + "72b-text-v1.5-q2_K", + "28GB" + ], + [ + "72b-text-v1.5-q3_K_S", + "33GB" + ], + [ + "72b-text-v1.5-q3_K_M", + "36GB" + ], + [ + "72b-text-v1.5-q4_1", + "45GB" + ], + [ + "72b-text-v1.5-q4_0", + "41GB" + ], + [ + "72b-text-v1.5-q4_K_S", + "42GB" + ], + [ + "72b-text-v1.5-fp16", + "145GB" + ], + [ + "72b-text-v1.5-q3_K_L", + "38GB" + ], [ "72b-text-q8_0", "77GB" ], + [ + "72b-text-v1.5-q5_K_M", + "51GB" + ], + [ + "72b-text-v1.5-q5_K_S", + "50GB" + ], + [ + "72b-text-v1.5-q6_K", + "59GB" + ], + [ + "72b-text-v1.5-q8_0", + "77GB" + ], [ "32b-chat", "18GB" @@ -4015,94 +4167,34 @@ "14b-chat", "8.2GB" ], - [ - "14b-chat-v1.5-fp16", - "28GB" - ], - [ - "14b-chat-v1.5-q2_K", - "6.1GB" - ], - [ - "14b-chat-v1.5-q3_K_L", - "7.8GB" - ], - [ - "14b-chat-v1.5-q3_K_M", - "7.4GB" - ], - [ - "14b-chat-v1.5-q3_K_S", - "6.9GB" - ], - [ - "14b-chat-v1.5-q4_0", - "8.2GB" - ], - [ - "14b-chat-v1.5-q4_1", - "9.0GB" - ], - [ - "14b-chat-v1.5-q4_K_M", - "9.2GB" - ], - [ - "14b-chat-v1.5-q4_K_S", - "8.6GB" - ], - [ - "14b-chat-v1.5-q5_0", - "9.9GB" - ], - [ - "14b-chat-v1.5-q5_1", - "11GB" - ], - [ - "14b-chat-v1.5-q5_K_M", - "11GB" - ], - [ - "14b-chat-v1.5-q5_K_S", - "10GB" - ], - [ - "14b-chat-q4_1", - "9.0GB" - ], - [ - "14b-chat-q3_K_L", - "8.0GB" - ], - [ - "14b-chat-q4_0", - "8.2GB" - ], - [ - "14b-chat-q3_K_S", - "6.9GB" - ], [ "14b-chat-fp16", "28GB" ], - [ - "14b-chat-v1.5-q8_0", - "15GB" - ], - [ - "14b-chat-v1.5-q6_K", - "12GB" - ], [ "14b-chat-q2_K", "6.0GB" ], + [ + "14b-chat-q3_K_L", + "8.0GB" + ], [ "14b-chat-q3_K_M", "7.7GB" ], + [ + "14b-chat-q3_K_S", + "6.9GB" + ], + [ + "14b-chat-q4_0", + "8.2GB" + ], + [ + "14b-chat-q4_1", + "9.0GB" + ], [ "14b-chat-q4_K_M", "9.4GB" @@ -4119,10 +4211,22 @@ "14b-chat-q5_1", "11GB" ], + [ + "14b-chat-v1.5-q2_K", + "6.1GB" + ], + [ + "14b-chat-q8_0", + "15GB" + ], [ "14b-chat-q5_K_M", "11GB" ], + [ + "14b-chat-v1.5-fp16", + "28GB" + ], [ "14b-chat-q5_K_S", "10GB" @@ -4132,7 +4236,55 @@ "12GB" ], [ - "14b-chat-q8_0", + "14b-chat-v1.5-q5_K_S", + "10GB" + ], + [ + "14b-chat-v1.5-q4_1", + "9.0GB" + ], + [ + "14b-chat-v1.5-q5_1", + "11GB" + ], + [ + "14b-chat-v1.5-q5_K_M", + "11GB" + ], + [ + "14b-chat-v1.5-q4_0", + "8.2GB" + ], + [ + "14b-chat-v1.5-q3_K_S", + "6.9GB" + ], + [ + "14b-chat-v1.5-q5_0", + "9.9GB" + ], + [ + "14b-chat-v1.5-q3_K_L", + "7.8GB" + ], + [ + "14b-chat-v1.5-q3_K_M", + "7.4GB" + ], + [ + "14b-chat-v1.5-q4_K_S", + "8.6GB" + ], + [ + "14b-chat-v1.5-q4_K_M", + "9.2GB" + ], + [ + "14b-chat-v1.5-q6_K", + "12GB" + ], + [ + "14b-chat-v1.5-q8_0", "15GB" ], [ @@ -4159,21 +4311,29 @@ "14b-text-q3_K_S", "6.9GB" ], - [ - "14b-text-v1.5-q4_K_M", - "9.2GB" - ], [ "14b-text-q4_0", "8.2GB" ], [ - "14b-text-q5_1", - "11GB" + "14b-text-q4_1", + "9.0GB" ], [ - "14b-text-v1.5-q3_K_S", - "6.9GB" + "14b-text-q4_K_M", + "9.4GB" + ], + [ + "14b-text-q4_K_S", + "8.6GB" + ], + [ + "14b-text-q5_0", + "9.9GB" + ], + [ + "14b-text-q5_1", + "11GB" ], [ "14b-text-q5_K_M", @@ -4183,69 +4343,61 @@ "14b-text-q5_K_S", "10GB" ], - [ - "14b-text-v1.5-q4_0", - "8.2GB" - ], [ "14b-text-q6_K", "12GB" ], [ - "14b-text-q8_0", - "15GB" - ], - [ - "14b-text-q5_0", - "9.9GB" - ], - [ - "14b-text-q4_1", - "9.0GB" - ], - [ - "14b-text-v1.5-q4_1", - "9.0GB" - ], - [ - "14b-text-q4_K_S", - "8.6GB" - ], - [ - "14b-text-q4_K_M", - "9.4GB" - ], - [ - "14b-text-v1.5-q3_K_L", - "7.8GB" - ], - [ - "14b-text-v1.5-q3_K_M", - "7.4GB" - ], - [ - "14b-text-v1.5-fp16", - "28GB" - ], - [ - "14b-text-v1.5-q2_K", - "6.1GB" + "14b-text-v1.5-q5_K_M", + "11GB" ], [ "14b-text-v1.5-q4_K_S", "8.6GB" ], [ - "14b-text-v1.5-q5_0", - "9.9GB" + "14b-text-v1.5-q4_1", + "9.0GB" ], [ "14b-text-v1.5-q5_1", "11GB" ], [ - "14b-text-v1.5-q5_K_M", - "11GB" + "14b-text-q8_0", + "15GB" + ], + [ + "14b-text-v1.5-fp16", + "28GB" + ], + [ + "14b-text-v1.5-q3_K_L", + "7.8GB" + ], + [ + "14b-text-v1.5-q3_K_S", + "6.9GB" + ], + [ + "14b-text-v1.5-q4_0", + "8.2GB" + ], + [ + "14b-text-v1.5-q2_K", + "6.1GB" + ], + [ + "14b-text-v1.5-q5_0", + "9.9GB" + ], + [ + "14b-text-v1.5-q3_K_M", + "7.4GB" + ], + [ + "14b-text-v1.5-q4_K_M", + "9.2GB" ], [ "14b-text-v1.5-q5_K_S", @@ -4292,80 +4444,80 @@ "5.0GB" ], [ - "7b-chat-v1.5-q5_1", - "5.8GB" - ], - [ - "7b-chat-v1.5-q3_K_M", - "3.9GB" - ], - [ - "7b-chat-q5_1", - "5.8GB" + "7b-chat-q4_K_M", + "4.9GB" ], [ "7b-chat-q4_K_S", "4.5GB" ], + [ + "7b-chat-q5_0", + "5.4GB" + ], + [ + "7b-chat-q5_1", + "5.8GB" + ], [ "7b-chat-q5_K_M", "5.7GB" ], [ - "7b-chat-q4_K_M", - "4.9GB" + "7b-chat-v1.5-q3_K_L", + "4.2GB" ], [ "7b-chat-q8_0", "8.2GB" ], [ - "7b-chat-v1.5-q4_1", - "5.0GB" - ], - [ - "7b-chat-v1.5-q4_K_S", - "4.5GB" + "7b-chat-v1.5-fp16", + "15GB" ], [ "7b-chat-v1.5-q2_K", "3.1GB" ], - [ - "7b-chat-v1.5-q3_K_S", - "3.6GB" - ], [ "7b-chat-q5_K_S", "5.4GB" ], - [ - "7b-chat-v1.5-q4_K_M", - "4.8GB" - ], - [ - "7b-chat-v1.5-q5_0", - "5.4GB" - ], [ "7b-chat-q6_K", "6.3GB" ], [ - "7b-chat-q5_0", - "5.4GB" + "7b-chat-v1.5-q5_1", + "5.8GB" + ], + [ + "7b-chat-v1.5-q3_K_S", + "3.6GB" + ], + [ + "7b-chat-v1.5-q4_K_S", + "4.5GB" ], [ "7b-chat-v1.5-q4_0", "4.5GB" ], [ - "7b-chat-v1.5-q3_K_L", - "4.2GB" + "7b-chat-v1.5-q4_K_M", + "4.8GB" ], [ - "7b-chat-v1.5-fp16", - "15GB" + "7b-chat-v1.5-q4_1", + "5.0GB" + ], + [ + "7b-chat-v1.5-q3_K_M", + "3.9GB" + ], + [ + "7b-chat-v1.5-q5_0", + "5.4GB" ], [ "7b-chat-v1.5-q5_K_M", @@ -4451,6 +4603,14 @@ "4b-chat", "2.3GB" ], + [ + "4b-text", + "2.3GB" + ], + [ + "1.8b-chat", + "1.1GB" + ], [ "7b-fp16", "15GB" @@ -4571,10 +4731,6 @@ "4b-chat-v1.5-q8_0", "4.2GB" ], - [ - "4b-text", - "2.3GB" - ], [ "4b-text-v1.5-fp16", "7.9GB" @@ -4635,58 +4791,14 @@ "4b-text-v1.5-q8_0", "4.2GB" ], - [ - "1.8b-chat", - "1.1GB" - ], - [ - "1.8b-chat-fp16", - "3.7GB" - ], - [ - "1.8b-chat-q2_K", - "853MB" - ], - [ - "1.8b-chat-q3_K_L", - "1.1GB" - ], - [ - "1.8b-chat-q3_K_M", - "1.0GB" - ], - [ - "1.8b-chat-q3_K_S", - "970MB" - ], - [ - "1.8b-chat-q4_0", - "1.1GB" - ], - [ - "1.8b-chat-v1.5-q4_K_S", - "1.2GB" - ], - [ - "1.8b-chat-v1.5-q4_1", - "1.2GB" - ], - [ - "1.8b-chat-v1.5-q4_K_M", - "1.2GB" - ], - [ - "1.8b-chat-v1.5-q3_K_S", - "970MB" - ], - [ - "1.8b-chat-q4_1", - "1.2GB" - ], [ "1.8b-chat-v1.5-fp16", "3.7GB" ], + [ + "1.8b-chat-v1.5-q2_K", + "863MB" + ], [ "1.8b-chat-v1.5-q3_K_L", "1.1GB" @@ -4695,45 +4807,25 @@ "1.8b-chat-v1.5-q3_K_M", "1.0GB" ], + [ + "1.8b-chat-v1.5-q3_K_S", + "970MB" + ], [ "1.8b-chat-v1.5-q4_0", "1.1GB" ], [ - "1.8b-chat-q4_K_S", + "1.8b-chat-v1.5-q4_1", "1.2GB" ], [ - "1.8b-chat-q5_K_M", - "1.4GB" - ], - [ - "1.8b-chat-q5_1", - "1.4GB" - ], - [ - "1.8b-chat-q8_0", - "2.0GB" - ], - [ - "1.8b-chat-q4_K_M", + "1.8b-chat-v1.5-q4_K_M", "1.2GB" ], [ - "1.8b-chat-v1.5-q2_K", - "863MB" - ], - [ - "1.8b-chat-q6_K", - "1.6GB" - ], - [ - "1.8b-chat-q5_K_S", - "1.3GB" - ], - [ - "1.8b-chat-q5_0", - "1.3GB" + "1.8b-chat-v1.5-q4_K_S", + "1.2GB" ], [ "1.8b-chat-v1.5-q5_0", @@ -4755,10 +4847,70 @@ "1.8b-chat-v1.5-q6_K", "1.6GB" ], + [ + "1.8b-chat-q6_K", + "1.6GB" + ], + [ + "1.8b-chat-q2_K", + "853MB" + ], [ "1.8b-chat-v1.5-q8_0", "2.0GB" ], + [ + "1.8b-chat-q3_K_L", + "1.1GB" + ], + [ + "1.8b-chat-q5_0", + "1.3GB" + ], + [ + "1.8b-chat-q4_K_S", + "1.2GB" + ], + [ + "1.8b-chat-q5_K_M", + "1.4GB" + ], + [ + "1.8b-chat-q4_K_M", + "1.2GB" + ], + [ + "1.8b-chat-q5_K_S", + "1.3GB" + ], + [ + "1.8b-chat-fp16", + "3.7GB" + ], + [ + "1.8b-chat-q4_1", + "1.2GB" + ], + [ + "1.8b-chat-q5_1", + "1.4GB" + ], + [ + "1.8b-chat-q3_K_M", + "1.0GB" + ], + [ + "1.8b-chat-q4_0", + "1.1GB" + ], + [ + "1.8b-chat-q3_K_S", + "970MB" + ], + [ + "1.8b-chat-q8_0", + "2.0GB" + ], [ "1.8b-text", "1.1GB" @@ -4772,101 +4924,101 @@ "863MB" ], [ - "1.8b-text-v1.5-q3_K_L", - "1.1GB" - ], - [ - "1.8b-text-v1.5-q3_K_M", - "1.0GB" - ], - [ - "1.8b-text-v1.5-q3_K_S", - "970MB" + "1.8b-text-q5_1", + "1.4GB" ], [ "1.8b-text-v1.5-q4_0", "1.1GB" ], [ - "1.8b-text-v1.5-q4_1", + "1.8b-text-v1.5-q8_0", + "2.0GB" + ], + [ + "1.8b-text-q4_0", + "1.1GB" + ], + [ + "1.8b-text-v1.5-q6_K", + "1.6GB" + ], + [ + "1.8b-text-v1.5-q5_1", + "1.4GB" + ], + [ + "1.8b-text-q4_K_M", "1.2GB" ], [ - "1.8b-text-v1.5-q4_K_M", + "1.8b-text-q3_K_S", + "970MB" + ], + [ + "1.8b-text-q4_K_S", + "1.2GB" + ], + [ + "1.8b-text-q2_K", + "853MB" + ], + [ + "1.8b-text-v1.5-q3_K_L", + "1.1GB" + ], + [ + "1.8b-text-q4_1", + "1.2GB" + ], + [ + "1.8b-text-v1.5-q3_K_M", + "1.0GB" + ], + [ + "1.8b-text-v1.5-q4_1", "1.2GB" ], [ "1.8b-text-v1.5-q4_K_S", "1.2GB" ], - [ - "1.8b-text-q5_0", - "1.3GB" - ], - [ - "1.8b-text-q4_1", - "1.2GB" - ], - [ - "1.8b-text-q4_K_S", - "1.2GB" - ], [ "1.8b-text-q3_K_M", "1.0GB" ], + [ + "1.8b-text-v1.5-q3_K_S", + "970MB" + ], + [ + "1.8b-text-v1.5-q4_K_M", + "1.2GB" + ], [ "1.8b-text-fp16", "3.7GB" ], - [ - "1.8b-text-q3_K_L", - "1.1GB" - ], - [ - "1.8b-text-q3_K_S", - "970MB" - ], - [ - "1.8b-text-v1.5-q6_K", - "1.6GB" - ], - [ - "1.8b-text-q4_0", - "1.1GB" - ], [ "1.8b-text-v1.5-q5_K_M", "1.4GB" ], + [ + "1.8b-text-q5_0", + "1.3GB" + ], [ "1.8b-text-v1.5-q5_K_S", "1.3GB" ], [ - "1.8b-text-q2_K", - "853MB" - ], - [ - "1.8b-text-v1.5-q8_0", - "2.0GB" - ], - [ - "1.8b-text-q4_K_M", - "1.2GB" - ], - [ - "1.8b-text-v1.5-q5_1", - "1.4GB" + "1.8b-text-q3_K_L", + "1.1GB" ], [ "1.8b-text-v1.5-q5_0", "1.3GB" ], - [ - "1.8b-text-q5_1", - "1.4GB" - ], [ "1.8b-text-q5_K_M", "1.4GB" @@ -6755,6 +6907,86 @@ "image": false, "author": "George Sung, Jarrad Hope" }, + "phi": { + "url": "https://ollama.com/library/phi", + "description": "Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities.", + "tags": [ + [ + "latest", + "1.6GB" + ], + [ + "2.7b", + "1.6GB" + ], + [ + "chat", + "1.6GB" + ], + [ + "2.7b-chat-v2-fp16", + "5.6GB" + ], + [ + "2.7b-chat-v2-q2_K", + "1.2GB" + ], + [ + "2.7b-chat-v2-q3_K_L", + "1.6GB" + ], + [ + "2.7b-chat-v2-q3_K_M", + "1.5GB" + ], + [ + "2.7b-chat-v2-q3_K_S", + "1.3GB" + ], + [ + "2.7b-chat-v2-q4_0", + "1.6GB" + ], + [ + "2.7b-chat-v2-q4_1", + "1.8GB" + ], + [ + "2.7b-chat-v2-q4_K_M", + "1.8GB" + ], + [ + "2.7b-chat-v2-q4_K_S", + "1.6GB" + ], + [ + "2.7b-chat-v2-q5_0", + "1.9GB" + ], + [ + "2.7b-chat-v2-q5_1", + "2.1GB" + ], + [ + "2.7b-chat-v2-q5_K_M", + "2.1GB" + ], + [ + "2.7b-chat-v2-q5_K_S", + "1.9GB" + ], + [ + "2.7b-chat-v2-q6_K", + "2.3GB" + ], + [ + "2.7b-chat-v2-q8_0", + "3.0GB" + ] + ], + "image": false, + "author": "Microsoft" + }, "deepseek-coder": { "url": "https://ollama.com/library/deepseek-coder", "description": "DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.", @@ -7171,86 +7403,6 @@ "image": false, "author": "DeepSeek Team" }, - "phi": { - "url": "https://ollama.com/library/phi", - "description": "Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities.", - "tags": [ - [ - "latest", - "1.6GB" - ], - [ - "2.7b", - "1.6GB" - ], - [ - "chat", - "1.6GB" - ], - [ - "2.7b-chat-v2-fp16", - "5.6GB" - ], - [ - "2.7b-chat-v2-q2_K", - "1.2GB" - ], - [ - "2.7b-chat-v2-q3_K_L", - "1.6GB" - ], - [ - "2.7b-chat-v2-q3_K_M", - "1.5GB" - ], - [ - "2.7b-chat-v2-q3_K_S", - "1.3GB" - ], - [ - "2.7b-chat-v2-q4_0", - "1.6GB" - ], - [ - "2.7b-chat-v2-q4_1", - "1.8GB" - ], - [ - "2.7b-chat-v2-q4_K_M", - "1.8GB" - ], - [ - "2.7b-chat-v2-q4_K_S", - "1.6GB" - ], - [ - "2.7b-chat-v2-q5_0", - "1.9GB" - ], - [ - "2.7b-chat-v2-q5_1", - "2.1GB" - ], - [ - "2.7b-chat-v2-q5_K_M", - "2.1GB" - ], - [ - "2.7b-chat-v2-q5_K_S", - "1.9GB" - ], - [ - "2.7b-chat-v2-q6_K", - "2.3GB" - ], - [ - "2.7b-chat-v2-q8_0", - "3.0GB" - ] - ], - "image": false, - "author": "Microsoft" - }, "dolphin-mistral": { "url": "https://ollama.com/library/dolphin-mistral", "description": "The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.", @@ -7543,109 +7695,33 @@ "7b-v2.2.1-q8_0", "7.7GB" ], - [ - "7b-v2.6", - "4.1GB" - ], [ "7b-v2.6-dpo-laser", "4.1GB" ], [ - "7b-v2.6-dpo-laser-fp16", - "14GB" - ], - [ - "7b-v2.6-dpo-laser-q2_K", - "3.1GB" - ], - [ - "7b-v2.6-dpo-laser-q3_K_L", - "3.8GB" - ], - [ - "7b-v2.6-dpo-laser-q3_K_M", - "3.5GB" - ], - [ - "7b-v2.6-dpo-laser-q3_K_S", - "3.2GB" - ], - [ - "7b-v2.6-dpo-laser-q4_0", + "7b-v2.6", "4.1GB" ], - [ - "7b-v2.6-dpo-laser-q4_1", - "4.6GB" - ], - [ - "7b-v2.6-dpo-laser-q4_K_M", - "4.4GB" - ], - [ - "7b-v2.6-dpo-laser-q4_K_S", - "4.1GB" - ], - [ - "7b-v2.6-q2_K", - "3.1GB" - ], - [ - "7b-v2.6-dpo-laser-q5_K_S", - "5.0GB" - ], - [ - "7b-v2.6-dpo-laser-q5_K_M", - "5.1GB" - ], - [ - "7b-v2.6-dpo-laser-q5_0", - "5.0GB" - ], [ "7b-v2.6-fp16", "14GB" ], [ - "7b-v2.6-dpo-laser-q6_K", - "5.9GB" + "7b-v2.6-q2_K", + "3.1GB" ], [ - "7b-v2.6-dpo-laser-q8_0", - "7.7GB" - ], - [ - "7b-v2.6-dpo-laser-q5_1", - "5.4GB" - ], - [ - "7b-v2.6-q6_K", - "5.9GB" - ], - [ - "7b-v2.6-q5_K_M", - "5.1GB" + "7b-v2.6-q3_K_L", + "3.8GB" ], [ "7b-v2.6-q3_K_M", "3.5GB" ], [ - "7b-v2.6-q5_0", - "5.0GB" - ], - [ - "7b-v2.6-q4_K_M", - "4.4GB" - ], - [ - "7b-v2.6-q4_K_S", - "4.1GB" - ], - [ - "7b-v2.6-q3_K_L", - "3.8GB" + "7b-v2.6-q3_K_S", + "3.2GB" ], [ "7b-v2.6-q4_0", @@ -7656,21 +7732,97 @@ "4.6GB" ], [ - "7b-v2.6-q5_1", - "5.4GB" + "7b-v2.6-dpo-laser-q8_0", + "7.7GB" ], [ - "7b-v2.6-q3_K_S", + "7b-v2.6-dpo-laser-q4_1", + "4.6GB" + ], + [ + "7b-v2.6-dpo-laser-q5_K_S", + "5.0GB" + ], + [ + "7b-v2.6-q4_K_M", + "4.4GB" + ], + [ + "7b-v2.6-q5_0", + "5.0GB" + ], + [ + "7b-v2.6-q5_K_M", + "5.1GB" + ], + [ + "7b-v2.6-dpo-laser-q5_0", + "5.0GB" + ], + [ + "7b-v2.6-dpo-laser-q4_K_M", + "4.4GB" + ], + [ + "7b-v2.6-dpo-laser-q3_K_S", "3.2GB" ], [ "7b-v2.6-q5_K_S", "5.0GB" ], + [ + "7b-v2.6-dpo-laser-fp16", + "14GB" + ], + [ + "7b-v2.6-dpo-laser-q3_K_M", + "3.5GB" + ], + [ + "7b-v2.6-dpo-laser-q6_K", + "5.9GB" + ], [ "7b-v2.6-q8_0", "7.7GB" ], + [ + "7b-v2.6-dpo-laser-q3_K_L", + "3.8GB" + ], + [ + "7b-v2.6-dpo-laser-q4_K_S", + "4.1GB" + ], + [ + "7b-v2.6-q4_K_S", + "4.1GB" + ], + [ + "7b-v2.6-q6_K", + "5.9GB" + ], + [ + "7b-v2.6-dpo-laser-q2_K", + "3.1GB" + ], + [ + "7b-v2.6-dpo-laser-q5_1", + "5.4GB" + ], + [ + "7b-v2.6-dpo-laser-q5_K_M", + "5.1GB" + ], + [ + "7b-v2.6-q5_1", + "5.4GB" + ], + [ + "7b-v2.6-dpo-laser-q4_0", + "4.1GB" + ], [ "7b-v2.8", "4.1GB" @@ -8312,11 +8464,11 @@ "75GB" ], [ - "8b-256k", + "8b-256k-v2.9", "4.7GB" ], [ - "8b-256k-v2.9", + "8b-256k", "4.7GB" ], [ @@ -8471,82 +8623,6 @@ "image": false, "author": "Mixedbread.ai" }, - "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.", - "tags": [ - [ - "latest", - "4.1GB" - ], - [ - "7b", - "4.1GB" - ], - [ - "7b-fp16", - "14GB" - ], - [ - "7b-q2_K", - "3.1GB" - ], - [ - "7b-q3_K_L", - "3.8GB" - ], - [ - "7b-q3_K_M", - "3.5GB" - ], - [ - "7b-q3_K_S", - "3.2GB" - ], - [ - "7b-q4_0", - "4.1GB" - ], - [ - "7b-q4_1", - "4.6GB" - ], - [ - "7b-q4_K_M", - "4.4GB" - ], - [ - "7b-q4_K_S", - "4.1GB" - ], - [ - "7b-q5_0", - "5.0GB" - ], - [ - "7b-q5_1", - "5.4GB" - ], - [ - "7b-q5_K_M", - "5.1GB" - ], - [ - "7b-q5_K_S", - "5.0GB" - ], - [ - "7b-q6_K", - "5.9GB" - ], - [ - "7b-q8_0", - "7.7GB" - ] - ], - "image": false, - "author": "Open Orca" - }, "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.", @@ -8591,26 +8667,6 @@ "15b-instruct-v0.1-q3_K_M", "8.0GB" ], - [ - "15b-instruct-q4_0", - "9.1GB" - ], - [ - "15b-instruct-v0.1-q4_K_S", - "9.2GB" - ], - [ - "15b-instruct-v0.1-q4_1", - "10GB" - ], - [ - "15b-instruct-v0.1-q5_0", - "11GB" - ], - [ - "15b-instruct-v0.1-q8_0", - "17GB" - ], [ "15b-instruct-v0.1-q3_K_S", "7.0GB" @@ -8620,16 +8676,20 @@ "9.1GB" ], [ - "15b-instruct-v0.1-q5_K_S", - "11GB" + "15b-instruct-v0.1-q4_1", + "10GB" ], [ "15b-instruct-v0.1-q4_K_M", "9.9GB" ], [ - "15b-instruct-v0.1-q6_K", - "13GB" + "15b-instruct-v0.1-q4_K_S", + "9.2GB" + ], + [ + "15b-instruct-v0.1-q5_0", + "11GB" ], [ "15b-instruct-v0.1-q5_1", @@ -8639,6 +8699,22 @@ "15b-instruct-v0.1-q5_K_M", "11GB" ], + [ + "15b-instruct-v0.1-q5_K_S", + "11GB" + ], + [ + "15b-instruct-v0.1-q6_K", + "13GB" + ], + [ + "15b-instruct-v0.1-q8_0", + "17GB" + ], + [ + "15b-instruct-q4_0", + "9.1GB" + ], [ "15b-fp16", "32GB" @@ -8823,6 +8899,786 @@ "image": false, "author": "BigCode" }, + "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.", + "tags": [ + [ + "latest", + "4.1GB" + ], + [ + "7b", + "4.1GB" + ], + [ + "7b-fp16", + "14GB" + ], + [ + "7b-q2_K", + "3.1GB" + ], + [ + "7b-q3_K_L", + "3.8GB" + ], + [ + "7b-q3_K_M", + "3.5GB" + ], + [ + "7b-q3_K_S", + "3.2GB" + ], + [ + "7b-q4_0", + "4.1GB" + ], + [ + "7b-q4_1", + "4.6GB" + ], + [ + "7b-q4_K_M", + "4.4GB" + ], + [ + "7b-q4_K_S", + "4.1GB" + ], + [ + "7b-q5_0", + "5.0GB" + ], + [ + "7b-q5_1", + "5.4GB" + ], + [ + "7b-q5_K_M", + "5.1GB" + ], + [ + "7b-q5_K_S", + "5.0GB" + ], + [ + "7b-q6_K", + "5.9GB" + ], + [ + "7b-q8_0", + "7.7GB" + ] + ], + "image": false, + "author": "Open Orca" + }, + "yi": { + "url": "https://ollama.com/library/yi", + "description": "Yi 1.5 is a high-performing, bilingual language model.", + "tags": [ + [ + "latest", + "3.5GB" + ], + [ + "34b", + "19GB" + ], + [ + "9b", + "5.0GB" + ], + [ + "6b", + "3.5GB" + ], + [ + "v1.5", + "3.5GB" + ], + [ + "34b-chat", + "19GB" + ], + [ + "34b-chat-v1.5-fp16", + "69GB" + ], + [ + "34b-chat-v1.5-q2_K", + "13GB" + ], + [ + "34b-chat-v1.5-q3_K_L", + "18GB" + ], + [ + "34b-chat-v1.5-q3_K_M", + "17GB" + ], + [ + "34b-chat-v1.5-q3_K_S", + "15GB" + ], + [ + "34b-chat-v1.5-q4_0", + "19GB" + ], + [ + "34b-chat-v1.5-q4_1", + "22GB" + ], + [ + "34b-chat-v1.5-q4_K_M", + "21GB" + ], + [ + "34b-chat-v1.5-q4_K_S", + "20GB" + ], + [ + "34b-chat-v1.5-q5_0", + "24GB" + ], + [ + "34b-chat-v1.5-q5_1", + "26GB" + ], + [ + "34b-chat-v1.5-q5_K_M", + "24GB" + ], + [ + "34b-chat-v1.5-q5_K_S", + "24GB" + ], + [ + "34b-chat-v1.5-q6_K", + "28GB" + ], + [ + "34b-chat-q6_K", + "28GB" + ], + [ + "34b-chat-q5_K_M", + "24GB" + ], + [ + "34b-chat-q4_K_S", + "20GB" + ], + [ + "34b-chat-q4_K_M", + "21GB" + ], + [ + "34b-chat-q3_K_M", + "17GB" + ], + [ + "34b-chat-q3_K_L", + "18GB" + ], + [ + "34b-chat-v1.5-q8_0", + "37GB" + ], + [ + "34b-chat-fp16", + "69GB" + ], + [ + "34b-chat-q4_0", + "19GB" + ], + [ + "34b-chat-q5_K_S", + "24GB" + ], + [ + "34b-chat-q4_1", + "22GB" + ], + [ + "34b-chat-q3_K_S", + "15GB" + ], + [ + "34b-chat-q2_K", + "15GB" + ], + [ + "34b-chat-q5_0", + "24GB" + ], + [ + "34b-chat-q5_1", + "26GB" + ], + [ + "34b-chat-q8_0", + "37GB" + ], + [ + "34b-v1.5", + "19GB" + ], + [ + "34b-v1.5-fp16", + "69GB" + ], + [ + "34b-v1.5-q2_K", + "13GB" + ], + [ + "34b-v1.5-q3_K_L", + "18GB" + ], + [ + "34b-v1.5-q3_K_M", + "17GB" + ], + [ + "34b-v1.5-q3_K_S", + "15GB" + ], + [ + "34b-v1.5-q4_0", + "19GB" + ], + [ + "34b-v1.5-q4_1", + "22GB" + ], + [ + "34b-v1.5-q4_K_M", + "21GB" + ], + [ + "34b-v1.5-q4_K_S", + "20GB" + ], + [ + "34b-v1.5-q5_0", + "24GB" + ], + [ + "34b-v1.5-q5_1", + "26GB" + ], + [ + "34b-v1.5-q5_K_M", + "24GB" + ], + [ + "34b-v1.5-q5_K_S", + "24GB" + ], + [ + "34b-v1.5-q6_K", + "28GB" + ], + [ + "34b-v1.5-q8_0", + "37GB" + ], + [ + "9b-chat", + "5.0GB" + ], + [ + "34b-q2_K", + "15GB" + ], + [ + "34b-q3_K_L", + "18GB" + ], + [ + "34b-q3_K_M", + "17GB" + ], + [ + "34b-q3_K_S", + "15GB" + ], + [ + "34b-q4_0", + "19GB" + ], + [ + "34b-q4_1", + "22GB" + ], + [ + "34b-q4_K_M", + "21GB" + ], + [ + "34b-q4_K_S", + "20GB" + ], + [ + "34b-q5_0", + "24GB" + ], + [ + "34b-q5_1", + "26GB" + ], + [ + "34b-q5_K_S", + "24GB" + ], + [ + "34b-q6_K", + "28GB" + ], + [ + "9b-chat-v1.5-fp16", + "18GB" + ], + [ + "9b-chat-v1.5-q2_K", + "3.4GB" + ], + [ + "9b-chat-v1.5-q3_K_L", + "4.7GB" + ], + [ + "9b-chat-v1.5-q3_K_M", + "4.3GB" + ], + [ + "9b-chat-v1.5-q3_K_S", + "3.9GB" + ], + [ + "9b-chat-v1.5-q4_0", + "5.0GB" + ], + [ + "9b-chat-v1.5-q4_1", + "5.6GB" + ], + [ + "9b-chat-v1.5-q4_K_M", + "5.3GB" + ], + [ + "9b-chat-v1.5-q4_K_S", + "5.1GB" + ], + [ + "9b-chat-v1.5-q5_0", + "6.1GB" + ], + [ + "9b-chat-v1.5-q5_1", + "6.6GB" + ], + [ + "9b-chat-v1.5-q5_K_M", + "6.3GB" + ], + [ + "9b-chat-v1.5-q5_K_S", + "6.1GB" + ], + [ + "9b-chat-v1.5-q6_K", + "7.2GB" + ], + [ + "9b-chat-v1.5-q8_0", + "9.4GB" + ], + [ + "9b-v1.5", + "5.0GB" + ], + [ + "9b-v1.5-fp16", + "18GB" + ], + [ + "9b-v1.5-q2_K", + "3.4GB" + ], + [ + "9b-v1.5-q3_K_L", + "4.7GB" + ], + [ + "9b-v1.5-q3_K_M", + "4.3GB" + ], + [ + "9b-v1.5-q3_K_S", + "3.9GB" + ], + [ + "9b-v1.5-q4_0", + "5.0GB" + ], + [ + "9b-v1.5-q4_1", + "5.6GB" + ], + [ + "9b-v1.5-q4_K_M", + "5.3GB" + ], + [ + "9b-v1.5-q4_K_S", + "5.1GB" + ], + [ + "9b-v1.5-q5_0", + "6.1GB" + ], + [ + "9b-v1.5-q5_1", + "6.6GB" + ], + [ + "9b-v1.5-q5_K_M", + "6.3GB" + ], + [ + "9b-v1.5-q5_K_S", + "6.1GB" + ], + [ + "9b-v1.5-q6_K", + "7.2GB" + ], + [ + "9b-v1.5-q8_0", + "9.4GB" + ], + [ + "6b-200k", + "3.5GB" + ], + [ + "6b-200k-fp16", + "12GB" + ], + [ + "6b-200k-q2_K", + "2.6GB" + ], + [ + "6b-200k-q3_K_L", + "3.2GB" + ], + [ + "6b-200k-q3_K_M", + "3.0GB" + ], + [ + "6b-200k-q3_K_S", + "2.7GB" + ], + [ + "6b-200k-q4_0", + "3.5GB" + ], + [ + "6b-200k-q4_1", + "3.8GB" + ], + [ + "6b-200k-q4_K_M", + "3.7GB" + ], + [ + "6b-200k-q4_K_S", + "3.5GB" + ], + [ + "6b-200k-q5_0", + "4.2GB" + ], + [ + "6b-200k-q5_1", + "4.6GB" + ], + [ + "6b-200k-q5_K_M", + "4.3GB" + ], + [ + "6b-200k-q5_K_S", + "4.2GB" + ], + [ + "6b-200k-q6_K", + "5.0GB" + ], + [ + "6b-200k-q8_0", + "6.4GB" + ], + [ + "6b-chat", + "3.5GB" + ], + [ + "6b-chat-fp16", + "12GB" + ], + [ + "6b-chat-q2_K", + "2.6GB" + ], + [ + "6b-chat-q3_K_L", + "3.2GB" + ], + [ + "6b-chat-q3_K_M", + "3.0GB" + ], + [ + "6b-chat-q3_K_S", + "2.7GB" + ], + [ + "6b-chat-q4_0", + "3.5GB" + ], + [ + "6b-chat-q4_1", + "3.8GB" + ], + [ + "6b-chat-q4_K_M", + "3.7GB" + ], + [ + "6b-chat-q4_K_S", + "3.5GB" + ], + [ + "6b-chat-q5_0", + "4.2GB" + ], + [ + "6b-chat-q5_1", + "4.6GB" + ], + [ + "6b-chat-q5_K_M", + "4.3GB" + ], + [ + "6b-chat-q5_K_S", + "4.2GB" + ], + [ + "6b-chat-q6_K", + "5.0GB" + ], + [ + "6b-chat-v1.5-q5_0", + "4.2GB" + ], + [ + "6b-chat-v1.5-q2_K", + "2.3GB" + ], + [ + "6b-chat-v1.5-q4_K_M", + "3.7GB" + ], + [ + "6b-chat-v1.5-q4_1", + "3.8GB" + ], + [ + "6b-chat-v1.5-q3_K_L", + "3.2GB" + ], + [ + "6b-chat-v1.5-q4_K_S", + "3.5GB" + ], + [ + "6b-chat-q8_0", + "6.4GB" + ], + [ + "6b-chat-v1.5-q3_K_S", + "2.7GB" + ], + [ + "6b-chat-v1.5-q3_K_M", + "3.0GB" + ], + [ + "6b-chat-v1.5-fp16", + "12GB" + ], + [ + "6b-chat-v1.5-q4_0", + "3.5GB" + ], + [ + "6b-chat-v1.5-q5_1", + "4.6GB" + ], + [ + "6b-chat-v1.5-q5_K_M", + "4.3GB" + ], + [ + "6b-chat-v1.5-q5_K_S", + "4.2GB" + ], + [ + "6b-chat-v1.5-q6_K", + "5.0GB" + ], + [ + "6b-chat-v1.5-q8_0", + "6.4GB" + ], + [ + "6b-v1.5", + "3.5GB" + ], + [ + "6b-v1.5-fp16", + "12GB" + ], + [ + "6b-v1.5-q2_K", + "2.3GB" + ], + [ + "6b-v1.5-q3_K_L", + "3.2GB" + ], + [ + "6b-v1.5-q3_K_M", + "3.0GB" + ], + [ + "6b-v1.5-q3_K_S", + "2.7GB" + ], + [ + "6b-v1.5-q4_0", + "3.5GB" + ], + [ + "6b-v1.5-q4_1", + "3.8GB" + ], + [ + "6b-v1.5-q4_K_M", + "3.7GB" + ], + [ + "6b-v1.5-q4_K_S", + "3.5GB" + ], + [ + "6b-v1.5-q5_0", + "4.2GB" + ], + [ + "6b-v1.5-q5_1", + "4.6GB" + ], + [ + "6b-v1.5-q5_K_M", + "4.3GB" + ], + [ + "6b-v1.5-q5_K_S", + "4.2GB" + ], + [ + "6b-v1.5-q6_K", + "5.0GB" + ], + [ + "6b-v1.5-q8_0", + "6.4GB" + ], + [ + "6b-fp16", + "12GB" + ], + [ + "6b-q2_K", + "2.6GB" + ], + [ + "6b-q3_K_L", + "3.2GB" + ], + [ + "6b-q3_K_M", + "3.0GB" + ], + [ + "6b-q3_K_S", + "2.7GB" + ], + [ + "6b-q4_0", + "3.5GB" + ], + [ + "6b-q4_1", + "3.8GB" + ], + [ + "6b-q4_K_M", + "3.7GB" + ], + [ + "6b-q4_K_S", + "3.5GB" + ], + [ + "6b-q5_0", + "4.2GB" + ], + [ + "6b-q5_1", + "4.6GB" + ], + [ + "6b-q5_K_M", + "4.3GB" + ], + [ + "6b-q5_K_S", + "4.2GB" + ], + [ + "6b-q6_K", + "5.0GB" + ], + [ + "6b-q8_0", + "6.4GB" + ] + ], + "image": false, + "author": "01.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.", @@ -8991,710 +9847,6 @@ "image": false, "author": "Hugging Face H4" }, - "yi": { - "url": "https://ollama.com/library/yi", - "description": "Yi 1.5 is a high-performing, bilingual language model.", - "tags": [ - [ - "latest", - "3.5GB" - ], - [ - "34b", - "19GB" - ], - [ - "9b", - "5.0GB" - ], - [ - "6b", - "3.5GB" - ], - [ - "v1.5", - "3.5GB" - ], - [ - "34b-chat", - "19GB" - ], - [ - "34b-chat-v1.5-fp16", - "69GB" - ], - [ - "34b-chat-v1.5-q2_K", - "13GB" - ], - [ - "34b-chat-v1.5-q3_K_L", - "18GB" - ], - [ - "34b-chat-v1.5-q3_K_M", - "17GB" - ], - [ - "34b-chat-v1.5-q3_K_S", - "15GB" - ], - [ - "34b-chat-v1.5-q4_0", - "19GB" - ], - [ - "34b-chat-q5_K_S", - "24GB" - ], - [ - "34b-chat-v1.5-q8_0", - "37GB" - ], - [ - "34b-chat-v1.5-q5_K_M", - "24GB" - ], - [ - "34b-chat-q4_K_M", - "21GB" - ], - [ - "34b-chat-q5_0", - "24GB" - ], - [ - "34b-chat-q2_K", - "15GB" - ], - [ - "34b-chat-q3_K_L", - "18GB" - ], - [ - "34b-chat-q4_1", - "22GB" - ], - [ - "34b-chat-v1.5-q4_K_M", - "21GB" - ], - [ - "34b-chat-fp16", - "69GB" - ], - [ - "34b-chat-v1.5-q5_K_S", - "24GB" - ], - [ - "34b-chat-v1.5-q5_0", - "24GB" - ], - [ - "34b-chat-q5_1", - "26GB" - ], - [ - "34b-chat-q5_K_M", - "24GB" - ], - [ - "34b-chat-q3_K_M", - "17GB" - ], - [ - "34b-chat-q4_K_S", - "20GB" - ], - [ - "34b-chat-v1.5-q4_1", - "22GB" - ], - [ - "34b-chat-q3_K_S", - "15GB" - ], - [ - "34b-chat-v1.5-q5_1", - "26GB" - ], - [ - "34b-chat-q4_0", - "19GB" - ], - [ - "34b-chat-v1.5-q4_K_S", - "20GB" - ], - [ - "34b-chat-v1.5-q6_K", - "28GB" - ], - [ - "34b-chat-q6_K", - "28GB" - ], - [ - "34b-chat-q8_0", - "37GB" - ], - [ - "34b-v1.5", - "19GB" - ], - [ - "34b-v1.5-fp16", - "69GB" - ], - [ - "34b-v1.5-q2_K", - "13GB" - ], - [ - "34b-v1.5-q3_K_L", - "18GB" - ], - [ - "34b-v1.5-q3_K_M", - "17GB" - ], - [ - "34b-v1.5-q3_K_S", - "15GB" - ], - [ - "34b-v1.5-q4_0", - "19GB" - ], - [ - "34b-v1.5-q4_1", - "22GB" - ], - [ - "34b-v1.5-q4_K_M", - "21GB" - ], - [ - "34b-v1.5-q4_K_S", - "20GB" - ], - [ - "34b-v1.5-q5_0", - "24GB" - ], - [ - "34b-v1.5-q5_1", - "26GB" - ], - [ - "34b-v1.5-q5_K_M", - "24GB" - ], - [ - "34b-v1.5-q5_K_S", - "24GB" - ], - [ - "34b-v1.5-q6_K", - "28GB" - ], - [ - "34b-v1.5-q8_0", - "37GB" - ], - [ - "9b-chat", - "5.0GB" - ], - [ - "9b-chat-v1.5-fp16", - "18GB" - ], - [ - "9b-chat-v1.5-q2_K", - "3.4GB" - ], - [ - "9b-chat-v1.5-q3_K_L", - "4.7GB" - ], - [ - "9b-chat-v1.5-q3_K_M", - "4.3GB" - ], - [ - "9b-chat-v1.5-q3_K_S", - "3.9GB" - ], - [ - "9b-chat-v1.5-q4_0", - "5.0GB" - ], - [ - "9b-chat-v1.5-q4_1", - "5.6GB" - ], - [ - "9b-chat-v1.5-q4_K_M", - "5.3GB" - ], - [ - "9b-chat-v1.5-q4_K_S", - "5.1GB" - ], - [ - "9b-chat-v1.5-q5_0", - "6.1GB" - ], - [ - "9b-chat-v1.5-q5_1", - "6.6GB" - ], - [ - "9b-chat-v1.5-q5_K_M", - "6.3GB" - ], - [ - "9b-chat-v1.5-q5_K_S", - "6.1GB" - ], - [ - "9b-chat-v1.5-q6_K", - "7.2GB" - ], - [ - "9b-chat-v1.5-q8_0", - "9.4GB" - ], - [ - "9b-v1.5", - "5.0GB" - ], - [ - "9b-v1.5-fp16", - "18GB" - ], - [ - "9b-v1.5-q2_K", - "3.4GB" - ], - [ - "9b-v1.5-q3_K_L", - "4.7GB" - ], - [ - "9b-v1.5-q3_K_M", - "4.3GB" - ], - [ - "9b-v1.5-q3_K_S", - "3.9GB" - ], - [ - "9b-v1.5-q4_0", - "5.0GB" - ], - [ - "9b-v1.5-q4_1", - "5.6GB" - ], - [ - "9b-v1.5-q4_K_M", - "5.3GB" - ], - [ - "9b-v1.5-q4_K_S", - "5.1GB" - ], - [ - "9b-v1.5-q5_0", - "6.1GB" - ], - [ - "9b-v1.5-q5_1", - "6.6GB" - ], - [ - "9b-v1.5-q5_K_M", - "6.3GB" - ], - [ - "9b-v1.5-q5_K_S", - "6.1GB" - ], - [ - "9b-v1.5-q6_K", - "7.2GB" - ], - [ - "9b-v1.5-q8_0", - "9.4GB" - ], - [ - "6b-200k", - "3.5GB" - ], - [ - "34b-q2_K", - "15GB" - ], - [ - "34b-q3_K_L", - "18GB" - ], - [ - "34b-q3_K_M", - "17GB" - ], - [ - "34b-q3_K_S", - "15GB" - ], - [ - "34b-q4_0", - "19GB" - ], - [ - "34b-q4_1", - "22GB" - ], - [ - "34b-q4_K_M", - "21GB" - ], - [ - "34b-q4_K_S", - "20GB" - ], - [ - "34b-q5_0", - "24GB" - ], - [ - "34b-q5_1", - "26GB" - ], - [ - "34b-q5_K_S", - "24GB" - ], - [ - "34b-q6_K", - "28GB" - ], - [ - "6b-200k-fp16", - "12GB" - ], - [ - "6b-200k-q2_K", - "2.6GB" - ], - [ - "6b-200k-q3_K_L", - "3.2GB" - ], - [ - "6b-200k-q3_K_M", - "3.0GB" - ], - [ - "6b-200k-q3_K_S", - "2.7GB" - ], - [ - "6b-200k-q4_0", - "3.5GB" - ], - [ - "6b-200k-q4_1", - "3.8GB" - ], - [ - "6b-200k-q4_K_M", - "3.7GB" - ], - [ - "6b-200k-q4_K_S", - "3.5GB" - ], - [ - "6b-200k-q5_0", - "4.2GB" - ], - [ - "6b-200k-q5_1", - "4.6GB" - ], - [ - "6b-200k-q5_K_M", - "4.3GB" - ], - [ - "6b-200k-q5_K_S", - "4.2GB" - ], - [ - "6b-200k-q6_K", - "5.0GB" - ], - [ - "6b-200k-q8_0", - "6.4GB" - ], - [ - "6b-chat", - "3.5GB" - ], - [ - "6b-chat-v1.5-fp16", - "12GB" - ], - [ - "6b-chat-v1.5-q2_K", - "2.3GB" - ], - [ - "6b-chat-v1.5-q3_K_L", - "3.2GB" - ], - [ - "6b-chat-v1.5-q3_K_M", - "3.0GB" - ], - [ - "6b-chat-v1.5-q3_K_S", - "2.7GB" - ], - [ - "6b-chat-v1.5-q4_0", - "3.5GB" - ], - [ - "6b-chat-v1.5-q4_1", - "3.8GB" - ], - [ - "6b-chat-v1.5-q4_K_M", - "3.7GB" - ], - [ - "6b-chat-q4_0", - "3.5GB" - ], - [ - "6b-chat-v1.5-q8_0", - "6.4GB" - ], - [ - "6b-chat-q3_K_L", - "3.2GB" - ], - [ - "6b-chat-v1.5-q5_K_S", - "4.2GB" - ], - [ - "6b-chat-v1.5-q4_K_S", - "3.5GB" - ], - [ - "6b-chat-v1.5-q5_K_M", - "4.3GB" - ], - [ - "6b-chat-v1.5-q5_1", - "4.6GB" - ], - [ - "6b-chat-fp16", - "12GB" - ], - [ - "6b-chat-q2_K", - "2.6GB" - ], - [ - "6b-chat-q3_K_M", - "3.0GB" - ], - [ - "6b-chat-v1.5-q6_K", - "5.0GB" - ], - [ - "6b-chat-q3_K_S", - "2.7GB" - ], - [ - "6b-chat-v1.5-q5_0", - "4.2GB" - ], - [ - "6b-chat-q4_K_S", - "3.5GB" - ], - [ - "6b-chat-q4_K_M", - "3.7GB" - ], - [ - "6b-chat-q4_1", - "3.8GB" - ], - [ - "6b-chat-q5_0", - "4.2GB" - ], - [ - "6b-chat-q5_1", - "4.6GB" - ], - [ - "6b-chat-q5_K_M", - "4.3GB" - ], - [ - "6b-chat-q5_K_S", - "4.2GB" - ], - [ - "6b-chat-q6_K", - "5.0GB" - ], - [ - "6b-chat-q8_0", - "6.4GB" - ], - [ - "6b-v1.5", - "3.5GB" - ], - [ - "6b-v1.5-fp16", - "12GB" - ], - [ - "6b-v1.5-q2_K", - "2.3GB" - ], - [ - "6b-v1.5-q3_K_L", - "3.2GB" - ], - [ - "6b-v1.5-q3_K_M", - "3.0GB" - ], - [ - "6b-v1.5-q3_K_S", - "2.7GB" - ], - [ - "6b-v1.5-q4_0", - "3.5GB" - ], - [ - "6b-v1.5-q4_1", - "3.8GB" - ], - [ - "6b-v1.5-q4_K_M", - "3.7GB" - ], - [ - "6b-v1.5-q4_K_S", - "3.5GB" - ], - [ - "6b-v1.5-q5_0", - "4.2GB" - ], - [ - "6b-v1.5-q5_1", - "4.6GB" - ], - [ - "6b-v1.5-q5_K_M", - "4.3GB" - ], - [ - "6b-v1.5-q5_K_S", - "4.2GB" - ], - [ - "6b-v1.5-q6_K", - "5.0GB" - ], - [ - "6b-v1.5-q8_0", - "6.4GB" - ], - [ - "6b-fp16", - "12GB" - ], - [ - "6b-q2_K", - "2.6GB" - ], - [ - "6b-q3_K_L", - "3.2GB" - ], - [ - "6b-q3_K_M", - "3.0GB" - ], - [ - "6b-q3_K_S", - "2.7GB" - ], - [ - "6b-q4_0", - "3.5GB" - ], - [ - "6b-q4_1", - "3.8GB" - ], - [ - "6b-q4_K_M", - "3.7GB" - ], - [ - "6b-q4_K_S", - "3.5GB" - ], - [ - "6b-q5_0", - "4.2GB" - ], - [ - "6b-q5_1", - "4.6GB" - ], - [ - "6b-q5_K_M", - "4.3GB" - ], - [ - "6b-q5_K_S", - "4.2GB" - ], - [ - "6b-q6_K", - "5.0GB" - ], - [ - "6b-q8_0", - "6.4GB" - ] - ], - "image": false, - "author": "01.AI" - }, "llama2-chinese": { "url": "https://ollama.com/library/llama2-chinese", "description": "Llama 2 based model fine tuned to improve Chinese dialogue ability.", @@ -9999,6 +10151,18 @@ "13b-v1.5-16k-q5_K_M", "9.2GB" ], + [ + "13b-v1.5-q3_K_S", + "5.7GB" + ], + [ + "13b-v1.5-q2_K", + "5.4GB" + ], + [ + "13b-v1.5-q3_K_M", + "6.3GB" + ], [ "13b-v1.5-16k-q5_K_S", "9.0GB" @@ -10008,32 +10172,16 @@ "11GB" ], [ - "13b-v1.5-q4_K_S", - "7.4GB" - ], - [ - "13b-v1.5-q3_K_S", - "5.7GB" - ], - [ - "13b-v1.5-q4_K_M", - "7.9GB" - ], - [ - "13b-v1.5-q3_K_M", - "6.3GB" + "13b-v1.5-q3_K_L", + "6.9GB" ], [ "13b-v1.5-16k-q8_0", "14GB" ], [ - "13b-v1.5-q3_K_L", - "6.9GB" - ], - [ - "13b-v1.5-q2_K", - "5.4GB" + "13b-v1.5-fp16", + "26GB" ], [ "13b-v1.5-q4_0", @@ -10044,8 +10192,12 @@ "8.2GB" ], [ - "13b-v1.5-fp16", - "26GB" + "13b-v1.5-q4_K_M", + "7.9GB" + ], + [ + "13b-v1.5-q4_K_S", + "7.4GB" ], [ "13b-v1.5-q5_0", @@ -10164,55 +10316,75 @@ "4.2GB" ], [ - "7b-v1.5-q4_K_M", - "4.1GB" + "7b-v1.5-16k-q8_0", + "7.2GB" + ], + [ + "7b-v1.5-16k-q5_K_M", + "4.8GB" + ], + [ + "7b-v1.5-q5_K_M", + "4.8GB" ], [ "7b-v1.5-q4_K_S", "3.9GB" ], [ - "7b-v1.5-q5_0", - "4.7GB" - ], - [ - "7b-v1.5-16k-q8_0", - "7.2GB" - ], - [ - "7b-v1.5-q5_1", - "5.1GB" - ], - [ - "7b-v1.5-16k-q3_K_L", - "3.6GB" + "7b-v1.5-16k-q4_1", + "4.2GB" ], [ "7b-v1.5-q6_K", "5.5GB" ], [ - "7b-v1.5-16k-q3_K_S", - "2.9GB" + "7b-v1.5-q5_K_S", + "4.7GB" ], [ - "7b-v1.5-16k-q4_1", - "4.2GB" + "7b-v1.5-q4_K_M", + "4.1GB" ], [ "7b-v1.5-q8_0", "7.2GB" ], [ - "7b-v1.5-16k-q5_K_S", - "4.7GB" + "7b-v1.5-16k-q3_K_S", + "2.9GB" + ], + [ + "7b-v1.5-16k-fp16", + "13GB" + ], + [ + "7b-v1.5-16k-q4_K_M", + "4.1GB" ], [ "7b-v1.5-16k-q2_K", "2.8GB" ], [ - "7b-v1.5-q5_K_S", + "7b-v1.5-16k-q4_0", + "3.8GB" + ], + [ + "7b-v1.5-16k-q4_K_S", + "3.9GB" + ], + [ + "7b-v1.5-16k-q3_K_L", + "3.6GB" + ], + [ + "7b-v1.5-16k-q5_K_S", + "4.7GB" + ], + [ + "7b-v1.5-16k-q5_0", "4.7GB" ], [ @@ -10220,37 +10392,17 @@ "3.3GB" ], [ - "7b-v1.5-16k-q5_K_M", - "4.8GB" + "7b-v1.5-q5_1", + "5.1GB" + ], + [ + "7b-v1.5-q5_0", + "4.7GB" ], [ "7b-v1.5-16k-q6_K", "5.5GB" ], - [ - "7b-v1.5-16k-q4_K_M", - "4.1GB" - ], - [ - "7b-v1.5-16k-q4_K_S", - "3.9GB" - ], - [ - "7b-v1.5-q5_K_M", - "4.8GB" - ], - [ - "7b-v1.5-16k-fp16", - "13GB" - ], - [ - "7b-v1.5-16k-q4_0", - "3.8GB" - ], - [ - "7b-v1.5-16k-q5_0", - "4.7GB" - ], [ "7b-v1.5-16k-q5_1", "5.1GB" @@ -10459,6 +10611,158 @@ "image": false, "author": "Nous Research" }, + "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", + "638MB" + ], + [ + "1.1b", + "638MB" + ], + [ + "chat", + "638MB" + ], + [ + "v0.6", + "638MB" + ], + [ + "v1", + "638MB" + ], + [ + "1.1b-chat", + "638MB" + ], + [ + "1.1b-chat-v0.6-fp16", + "2.2GB" + ], + [ + "1.1b-chat-v0.6-q2_K", + "483MB" + ], + [ + "1.1b-chat-v0.6-q3_K_L", + "593MB" + ], + [ + "1.1b-chat-v0.6-q3_K_M", + "551MB" + ], + [ + "1.1b-chat-v0.6-q3_K_S", + "500MB" + ], + [ + "1.1b-chat-v0.6-q4_0", + "638MB" + ], + [ + "1.1b-chat-v0.6-q4_1", + "702MB" + ], + [ + "1.1b-chat-v0.6-q4_K_M", + "669MB" + ], + [ + "1.1b-chat-v0.6-q4_K_S", + "644MB" + ], + [ + "1.1b-chat-v0.6-q5_0", + "767MB" + ], + [ + "1.1b-chat-v0.6-q5_1", + "832MB" + ], + [ + "1.1b-chat-v0.6-q5_K_M", + "783MB" + ], + [ + "1.1b-chat-v0.6-q5_K_S", + "767MB" + ], + [ + "1.1b-chat-v0.6-q6_K", + "904MB" + ], + [ + "1.1b-chat-v0.6-q8_0", + "1.2GB" + ], + [ + "1.1b-chat-v1-fp16", + "2.2GB" + ], + [ + "1.1b-chat-v1-q2_K", + "483MB" + ], + [ + "1.1b-chat-v1-q3_K_L", + "593MB" + ], + [ + "1.1b-chat-v1-q3_K_M", + "551MB" + ], + [ + "1.1b-chat-v1-q3_K_S", + "500MB" + ], + [ + "1.1b-chat-v1-q4_0", + "638MB" + ], + [ + "1.1b-chat-v1-q4_1", + "702MB" + ], + [ + "1.1b-chat-v1-q4_K_M", + "669MB" + ], + [ + "1.1b-chat-v1-q4_K_S", + "644MB" + ], + [ + "1.1b-chat-v1-q5_0", + "767MB" + ], + [ + "1.1b-chat-v1-q5_1", + "832MB" + ], + [ + "1.1b-chat-v1-q5_K_M", + "783MB" + ], + [ + "1.1b-chat-v1-q5_K_S", + "767MB" + ], + [ + "1.1b-chat-v1-q6_K", + "904MB" + ], + [ + "1.1b-chat-v1-q8_0", + "1.2GB" + ] + ], + "image": false, + "author": "TinyLlama Team" + }, "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.", @@ -10663,158 +10967,6 @@ "image": false, "author": "Eric Hartford" }, - "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", - "638MB" - ], - [ - "1.1b", - "638MB" - ], - [ - "chat", - "638MB" - ], - [ - "v0.6", - "638MB" - ], - [ - "v1", - "638MB" - ], - [ - "1.1b-chat", - "638MB" - ], - [ - "1.1b-chat-v0.6-fp16", - "2.2GB" - ], - [ - "1.1b-chat-v0.6-q2_K", - "483MB" - ], - [ - "1.1b-chat-v0.6-q3_K_L", - "593MB" - ], - [ - "1.1b-chat-v0.6-q3_K_M", - "551MB" - ], - [ - "1.1b-chat-v0.6-q3_K_S", - "500MB" - ], - [ - "1.1b-chat-v0.6-q4_0", - "638MB" - ], - [ - "1.1b-chat-v0.6-q4_1", - "702MB" - ], - [ - "1.1b-chat-v0.6-q4_K_M", - "669MB" - ], - [ - "1.1b-chat-v0.6-q4_K_S", - "644MB" - ], - [ - "1.1b-chat-v0.6-q5_0", - "767MB" - ], - [ - "1.1b-chat-v0.6-q5_1", - "832MB" - ], - [ - "1.1b-chat-v0.6-q5_K_M", - "783MB" - ], - [ - "1.1b-chat-v0.6-q5_K_S", - "767MB" - ], - [ - "1.1b-chat-v0.6-q6_K", - "904MB" - ], - [ - "1.1b-chat-v0.6-q8_0", - "1.2GB" - ], - [ - "1.1b-chat-v1-fp16", - "2.2GB" - ], - [ - "1.1b-chat-v1-q2_K", - "483MB" - ], - [ - "1.1b-chat-v1-q3_K_L", - "593MB" - ], - [ - "1.1b-chat-v1-q3_K_M", - "551MB" - ], - [ - "1.1b-chat-v1-q3_K_S", - "500MB" - ], - [ - "1.1b-chat-v1-q4_0", - "638MB" - ], - [ - "1.1b-chat-v1-q4_1", - "702MB" - ], - [ - "1.1b-chat-v1-q4_K_M", - "669MB" - ], - [ - "1.1b-chat-v1-q4_K_S", - "644MB" - ], - [ - "1.1b-chat-v1-q5_0", - "767MB" - ], - [ - "1.1b-chat-v1-q5_1", - "832MB" - ], - [ - "1.1b-chat-v1-q5_K_M", - "783MB" - ], - [ - "1.1b-chat-v1-q5_K_S", - "767MB" - ], - [ - "1.1b-chat-v1-q6_K", - "904MB" - ], - [ - "1.1b-chat-v1-q8_0", - "1.2GB" - ] - ], - "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.", @@ -11055,6 +11207,10 @@ "3b-base", "1.8GB" ], + [ + "1b-base", + "726MB" + ], [ "15b-fp16", "32GB" @@ -11235,10 +11391,6 @@ "3b-base-q8_0", "3.4GB" ], - [ - "1b-base", - "726MB" - ], [ "1b-base-fp16", "2.5GB" @@ -11411,6 +11563,10 @@ "7b", "4.1GB" ], + [ + "7b-v3.5-1210", + "4.1GB" + ], [ "7b-v3.5", "4.1GB" @@ -11420,27 +11576,87 @@ "4.1GB" ], [ - "7b-v3.5-1210", - "4.1GB" + "7b-v3.5-fp16", + "14GB" ], [ - "7b-v3.5-0106-fp16", - "14GB" + "7b-v3.5-q2_K", + "3.1GB" + ], + [ + "7b-v3.5-0106-q4_K_M", + "4.4GB" + ], + [ + "7b-v3.5-q5_0", + "5.0GB" + ], + [ + "7b-v3.5-q4_1", + "4.6GB" + ], + [ + "7b-v3.5-q3_K_L", + "3.8GB" + ], + [ + "7b-v3.5-q5_1", + "5.4GB" + ], + [ + "7b-v3.5-q5_K_M", + "5.1GB" ], [ "7b-v3.5-0106-q2_K", "3.1GB" ], [ - "7b-v3.5-0106-q3_K_L", - "3.8GB" + "7b-v3.5-q4_0", + "4.1GB" ], [ "7b-v3.5-0106-q3_K_M", "3.5GB" ], [ - "7b-v3.5-0106-q3_K_S", + "7b-v3.5-q6_K", + "5.9GB" + ], + [ + "7b-v3.5-q3_K_M", + "3.5GB" + ], + [ + "7b-v3.5-0106-fp16", + "14GB" + ], + [ + "7b-v3.5-q4_K_M", + "4.4GB" + ], + [ + "7b-v3.5-q8_0", + "7.7GB" + ], + [ + "7b-v3.5-0106-q4_1", + "4.6GB" + ], + [ + "7b-v3.5-0106-q3_K_L", + "3.8GB" + ], + [ + "7b-v3.5-q5_K_S", + "5.0GB" + ], + [ + "7b-v3.5-q4_K_S", + "4.1GB" + ], + [ + "7b-v3.5-q3_K_S", "3.2GB" ], [ @@ -11448,12 +11664,8 @@ "4.1GB" ], [ - "7b-v3.5-0106-q4_1", - "4.6GB" - ], - [ - "7b-v3.5-0106-q4_K_M", - "4.4GB" + "7b-v3.5-0106-q3_K_S", + "3.2GB" ], [ "7b-v3.5-0106-q4_K_S", @@ -11539,74 +11751,162 @@ "7b-v3.5-1210-q6_K", "5.9GB" ], - [ - "7b-v3.5-q4_1", - "4.6GB" - ], - [ - "7b-v3.5-q3_K_M", - "3.5GB" - ], - [ - "7b-v3.5-q2_K", - "3.1GB" - ], - [ - "7b-v3.5-q3_K_L", - "3.8GB" - ], - [ - "7b-v3.5-q4_0", - "4.1GB" - ], [ "7b-v3.5-1210-q8_0", "7.7GB" - ], - [ - "7b-v3.5-fp16", - "14GB" - ], - [ - "7b-v3.5-q3_K_S", - "3.2GB" - ], - [ - "7b-v3.5-q4_K_M", - "4.4GB" - ], - [ - "7b-v3.5-q4_K_S", - "4.1GB" - ], - [ - "7b-v3.5-q5_0", - "5.0GB" - ], - [ - "7b-v3.5-q5_1", - "5.4GB" - ], - [ - "7b-v3.5-q5_K_M", - "5.1GB" - ], - [ - "7b-v3.5-q5_K_S", - "5.0GB" - ], - [ - "7b-v3.5-q6_K", - "5.9GB" - ], - [ - "7b-v3.5-q8_0", - "7.7GB" ] ], "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", + "4.8GB" + ], + [ + "35b", + "20GB" + ], + [ + "8b", + "4.8GB" + ], + [ + "35b-23", + "20GB" + ], + [ + "35b-23-f16", + "70GB" + ], + [ + "35b-23-q2_K", + "14GB" + ], + [ + "35b-23-q3_K_L", + "19GB" + ], + [ + "35b-23-q3_K_M", + "18GB" + ], + [ + "35b-23-q3_K_S", + "16GB" + ], + [ + "35b-23-q4_0", + "20GB" + ], + [ + "35b-23-q4_1", + "22GB" + ], + [ + "35b-23-q4_K_M", + "22GB" + ], + [ + "35b-23-q4_K_S", + "20GB" + ], + [ + "35b-23-q5_0", + "24GB" + ], + [ + "35b-23-q5_1", + "26GB" + ], + [ + "35b-23-q5_K_M", + "25GB" + ], + [ + "35b-23-q5_K_S", + "24GB" + ], + [ + "35b-23-q6_K", + "29GB" + ], + [ + "35b-23-q8_0", + "37GB" + ], + [ + "8b-23-f16", + "16GB" + ], + [ + "8b-23", + "4.8GB" + ], + [ + "8b-23-q2_K", + "3.4GB" + ], + [ + "8b-23-q3_K_L", + "4.5GB" + ], + [ + "8b-23-q3_K_M", + "4.2GB" + ], + [ + "8b-23-q3_K_S", + "3.9GB" + ], + [ + "8b-23-q4_0", + "4.8GB" + ], + [ + "8b-23-q4_1", + "5.2GB" + ], + [ + "8b-23-q4_K_M", + "5.1GB" + ], + [ + "8b-23-q4_K_S", + "4.8GB" + ], + [ + "8b-23-q5_0", + "5.7GB" + ], + [ + "8b-23-q5_1", + "6.1GB" + ], + [ + "8b-23-q5_K_M", + "5.8GB" + ], + [ + "8b-23-q5_K_S", + "5.7GB" + ], + [ + "8b-23-q6_K", + "6.6GB" + ], + [ + "8b-23-q8_0", + "8.5GB" + ] + ], + "image": false, + "author": "Cohere" + }, "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.", @@ -12391,214 +12691,6 @@ "image": false, "author": "Alibaba" }, - "neural-chat": { - "url": "https://ollama.com/library/neural-chat", - "description": "A fine-tuned model based on Mistral with good coverage of domain and language.", - "tags": [ - [ - "latest", - "4.1GB" - ], - [ - "7b", - "4.1GB" - ], - [ - "7b-v3.1", - "4.1GB" - ], - [ - "7b-v3.1-fp16", - "14GB" - ], - [ - "7b-v3.1-q2_K", - "3.1GB" - ], - [ - "7b-v3.1-q3_K_L", - "3.8GB" - ], - [ - "7b-v3.1-q3_K_M", - "3.5GB" - ], - [ - "7b-v3.1-q3_K_S", - "3.2GB" - ], - [ - "7b-v3.1-q4_0", - "4.1GB" - ], - [ - "7b-v3.1-q4_1", - "4.6GB" - ], - [ - "7b-v3.1-q4_K_M", - "4.4GB" - ], - [ - "7b-v3.1-q4_K_S", - "4.1GB" - ], - [ - "7b-v3.1-q5_0", - "5.0GB" - ], - [ - "7b-v3.1-q5_1", - "5.4GB" - ], - [ - "7b-v3.1-q5_K_M", - "5.1GB" - ], - [ - "7b-v3.1-q5_K_S", - "5.0GB" - ], - [ - "7b-v3.1-q6_K", - "5.9GB" - ], - [ - "7b-v3.1-q8_0", - "7.7GB" - ], - [ - "7b-v3.2", - "4.1GB" - ], - [ - "7b-v3.2-fp16", - "14GB" - ], - [ - "7b-v3.2-q2_K", - "3.1GB" - ], - [ - "7b-v3.2-q3_K_L", - "3.8GB" - ], - [ - "7b-v3.2-q3_K_M", - "3.5GB" - ], - [ - "7b-v3.2-q3_K_S", - "3.2GB" - ], - [ - "7b-v3.2-q4_0", - "4.1GB" - ], - [ - "7b-v3.2-q4_1", - "4.6GB" - ], - [ - "7b-v3.2-q4_K_M", - "4.4GB" - ], - [ - "7b-v3.2-q4_K_S", - "4.1GB" - ], - [ - "7b-v3.2-q5_0", - "5.0GB" - ], - [ - "7b-v3.2-q5_1", - "5.4GB" - ], - [ - "7b-v3.2-q5_K_M", - "5.1GB" - ], - [ - "7b-v3.2-q5_K_S", - "5.0GB" - ], - [ - "7b-v3.2-q6_K", - "5.9GB" - ], - [ - "7b-v3.2-q8_0", - "7.7GB" - ], - [ - "7b-v3.3", - "4.1GB" - ], - [ - "7b-v3.3-fp16", - "14GB" - ], - [ - "7b-v3.3-q2_K", - "3.1GB" - ], - [ - "7b-v3.3-q3_K_L", - "3.8GB" - ], - [ - "7b-v3.3-q3_K_M", - "3.5GB" - ], - [ - "7b-v3.3-q3_K_S", - "3.2GB" - ], - [ - "7b-v3.3-q4_0", - "4.1GB" - ], - [ - "7b-v3.3-q4_1", - "4.6GB" - ], - [ - "7b-v3.3-q4_K_M", - "4.4GB" - ], - [ - "7b-v3.3-q4_K_S", - "4.1GB" - ], - [ - "7b-v3.3-q5_0", - "5.0GB" - ], - [ - "7b-v3.3-q5_1", - "5.4GB" - ], - [ - "7b-v3.3-q5_K_M", - "5.1GB" - ], - [ - "7b-v3.3-q5_K_S", - "5.0GB" - ], - [ - "7b-v3.3-q6_K", - "5.9GB" - ], - [ - "7b-v3.3-q8_0", - "7.7GB" - ] - ], - "image": false, - "author": "Intel" - }, "wizard-math": { "url": "https://ollama.com/library/wizard-math", "description": "Model focused on math and logic problems", @@ -12863,6 +12955,214 @@ "image": false, "author": "WizardLM Team" }, + "neural-chat": { + "url": "https://ollama.com/library/neural-chat", + "description": "A fine-tuned model based on Mistral with good coverage of domain and language.", + "tags": [ + [ + "latest", + "4.1GB" + ], + [ + "7b", + "4.1GB" + ], + [ + "7b-v3.1", + "4.1GB" + ], + [ + "7b-v3.1-fp16", + "14GB" + ], + [ + "7b-v3.1-q2_K", + "3.1GB" + ], + [ + "7b-v3.1-q3_K_L", + "3.8GB" + ], + [ + "7b-v3.1-q3_K_M", + "3.5GB" + ], + [ + "7b-v3.1-q3_K_S", + "3.2GB" + ], + [ + "7b-v3.1-q4_0", + "4.1GB" + ], + [ + "7b-v3.1-q4_1", + "4.6GB" + ], + [ + "7b-v3.1-q4_K_M", + "4.4GB" + ], + [ + "7b-v3.1-q4_K_S", + "4.1GB" + ], + [ + "7b-v3.1-q5_0", + "5.0GB" + ], + [ + "7b-v3.1-q5_1", + "5.4GB" + ], + [ + "7b-v3.1-q5_K_M", + "5.1GB" + ], + [ + "7b-v3.1-q5_K_S", + "5.0GB" + ], + [ + "7b-v3.1-q6_K", + "5.9GB" + ], + [ + "7b-v3.1-q8_0", + "7.7GB" + ], + [ + "7b-v3.2", + "4.1GB" + ], + [ + "7b-v3.2-fp16", + "14GB" + ], + [ + "7b-v3.2-q2_K", + "3.1GB" + ], + [ + "7b-v3.2-q3_K_L", + "3.8GB" + ], + [ + "7b-v3.2-q3_K_M", + "3.5GB" + ], + [ + "7b-v3.2-q3_K_S", + "3.2GB" + ], + [ + "7b-v3.2-q4_0", + "4.1GB" + ], + [ + "7b-v3.2-q4_1", + "4.6GB" + ], + [ + "7b-v3.2-q4_K_M", + "4.4GB" + ], + [ + "7b-v3.2-q4_K_S", + "4.1GB" + ], + [ + "7b-v3.2-q5_0", + "5.0GB" + ], + [ + "7b-v3.2-q5_1", + "5.4GB" + ], + [ + "7b-v3.2-q5_K_M", + "5.1GB" + ], + [ + "7b-v3.2-q5_K_S", + "5.0GB" + ], + [ + "7b-v3.2-q6_K", + "5.9GB" + ], + [ + "7b-v3.2-q8_0", + "7.7GB" + ], + [ + "7b-v3.3", + "4.1GB" + ], + [ + "7b-v3.3-fp16", + "14GB" + ], + [ + "7b-v3.3-q2_K", + "3.1GB" + ], + [ + "7b-v3.3-q3_K_L", + "3.8GB" + ], + [ + "7b-v3.3-q3_K_M", + "3.5GB" + ], + [ + "7b-v3.3-q3_K_S", + "3.2GB" + ], + [ + "7b-v3.3-q4_0", + "4.1GB" + ], + [ + "7b-v3.3-q4_1", + "4.6GB" + ], + [ + "7b-v3.3-q4_K_M", + "4.4GB" + ], + [ + "7b-v3.3-q4_K_S", + "4.1GB" + ], + [ + "7b-v3.3-q5_0", + "5.0GB" + ], + [ + "7b-v3.3-q5_1", + "5.4GB" + ], + [ + "7b-v3.3-q5_K_M", + "5.1GB" + ], + [ + "7b-v3.3-q5_K_S", + "5.0GB" + ], + [ + "7b-v3.3-q6_K", + "5.9GB" + ], + [ + "7b-v3.3-q8_0", + "7.7GB" + ] + ], + "image": false, + "author": "Intel" + }, "stablelm2": { "url": "https://ollama.com/library/stablelm2", "description": "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.", @@ -12959,10 +13259,6 @@ "1.6b-chat", "983MB" ], - [ - "1.6b-zephyr", - "983MB" - ], [ "12b-fp16", "24GB" @@ -13083,6 +13379,10 @@ "1.6b-chat-q8_0", "1.8GB" ], + [ + "1.6b-zephyr", + "983MB" + ], [ "1.6b-zephyr-fp16", "3.3GB" @@ -13207,54 +13507,6 @@ "image": false, "author": "Stability AI" }, - "all-minilm": { - "url": "https://ollama.com/library/all-minilm", - "description": "Embedding models on very large sentence level datasets.", - "tags": [ - [ - "latest", - "46MB" - ], - [ - "33m", - "67MB" - ], - [ - "22m", - "46MB" - ], - [ - "l12", - "67MB" - ], - [ - "l6", - "46MB" - ], - [ - "v2", - "46MB" - ], - [ - "33m-l12-v2-fp16", - "67MB" - ], - [ - "22m-l6-v2-fp16", - "46MB" - ], - [ - "l12-v2", - "67MB" - ], - [ - "l6-v2", - "46MB" - ] - ], - "image": false, - "author": "Sentence Transformers" - }, "granite-code": { "url": "https://ollama.com/library/granite-code", "description": "A family of open foundation models by IBM for Code Intelligence", @@ -13279,14 +13531,14 @@ "3b", "2.0GB" ], - [ - "34b-base", - "19GB" - ], [ "34b-base-f16", "68GB" ], + [ + "34b-base", + "19GB" + ], [ "34b-base-q2_K", "13GB" @@ -13343,14 +13595,14 @@ "34b-base-q8_0", "36GB" ], - [ - "34b-instruct", - "19GB" - ], [ "34b-instruct-f16", "68GB" ], + [ + "34b-instruct", + "19GB" + ], [ "34b-instruct-q2_K", "13GB" @@ -13539,14 +13791,14 @@ "20b-instruct-q8_0", "21GB" ], - [ - "8b-base", - "4.6GB" - ], [ "8b-base-f16", "16GB" ], + [ + "8b-base", + "4.6GB" + ], [ "8b-base-fp16", "16GB" @@ -13675,14 +13927,14 @@ "8b-instruct-q8_0", "8.6GB" ], - [ - "3b-base", - "2.0GB" - ], [ "3b-base-f16", "7.0GB" ], + [ + "3b-base", + "2.0GB" + ], [ "3b-base-fp16", "7.0GB" @@ -13815,6 +14067,54 @@ "image": false, "author": "IBM for Code Intelligence" }, + "all-minilm": { + "url": "https://ollama.com/library/all-minilm", + "description": "Embedding models on very large sentence level datasets.", + "tags": [ + [ + "latest", + "46MB" + ], + [ + "33m", + "67MB" + ], + [ + "22m", + "46MB" + ], + [ + "l12", + "67MB" + ], + [ + "l6", + "46MB" + ], + [ + "v2", + "46MB" + ], + [ + "33m-l12-v2-fp16", + "67MB" + ], + [ + "22m-l6-v2-fp16", + "46MB" + ], + [ + "l12-v2", + "67MB" + ], + [ + "l6-v2", + "46MB" + ] + ], + "image": false, + "author": "Sentence Transformers" + }, "phind-codellama": { "url": "https://ollama.com/library/phind-codellama", "description": "Code generation model based on Code Llama.", @@ -14927,270 +15227,6 @@ "image": false, "author": "Berkeley Nest" }, - "deepseek-llm": { - "url": "https://ollama.com/library/deepseek-llm", - "description": "An advanced language model crafted with 2 trillion bilingual tokens.", - "tags": [ - [ - "latest", - "4.0GB" - ], - [ - "67b", - "38GB" - ], - [ - "7b", - "4.0GB" - ], - [ - "67b-base", - "38GB" - ], - [ - "67b-base-fp16", - "135GB" - ], - [ - "67b-base-q2_K", - "28GB" - ], - [ - "67b-base-q3_K_L", - "36GB" - ], - [ - "67b-base-q3_K_M", - "33GB" - ], - [ - "67b-base-q3_K_S", - "29GB" - ], - [ - "67b-base-q4_0", - "38GB" - ], - [ - "67b-base-q4_1", - "42GB" - ], - [ - "67b-base-q4_K_M", - "40GB" - ], - [ - "67b-base-q4_K_S", - "38GB" - ], - [ - "67b-base-q5_0", - "46GB" - ], - [ - "67b-base-q5_1", - "51GB" - ], - [ - "67b-base-q5_K_M", - "48GB" - ], - [ - "67b-base-q5_K_S", - "46GB" - ], - [ - "67b-base-q6_K", - "55GB" - ], - [ - "67b-base-q8_0", - "72GB" - ], - [ - "67b-chat", - "38GB" - ], - [ - "67b-chat-fp16", - "135GB" - ], - [ - "67b-chat-q2_K", - "28GB" - ], - [ - "67b-chat-q3_K_L", - "36GB" - ], - [ - "67b-chat-q3_K_M", - "33GB" - ], - [ - "67b-chat-q3_K_S", - "29GB" - ], - [ - "67b-chat-q4_0", - "38GB" - ], - [ - "67b-chat-q4_1", - "42GB" - ], - [ - "67b-chat-q4_K_M", - "40GB" - ], - [ - "67b-chat-q4_K_S", - "38GB" - ], - [ - "67b-chat-q5_0", - "46GB" - ], - [ - "67b-chat-q5_1", - "51GB" - ], - [ - "67b-chat-q5_K_S", - "46GB" - ], - [ - "7b-base", - "4.0GB" - ], - [ - "7b-base-fp16", - "14GB" - ], - [ - "7b-base-q2_K", - "3.0GB" - ], - [ - "7b-base-q3_K_L", - "3.7GB" - ], - [ - "7b-base-q3_K_M", - "3.5GB" - ], - [ - "7b-base-q3_K_S", - "3.1GB" - ], - [ - "7b-base-q4_0", - "4.0GB" - ], - [ - "7b-base-q4_1", - "4.4GB" - ], - [ - "7b-base-q4_K_M", - "4.2GB" - ], - [ - "7b-base-q4_K_S", - "4.0GB" - ], - [ - "7b-base-q5_0", - "4.8GB" - ], - [ - "7b-base-q5_1", - "5.2GB" - ], - [ - "7b-base-q5_K_M", - "4.9GB" - ], - [ - "7b-base-q5_K_S", - "4.8GB" - ], - [ - "7b-base-q6_K", - "5.7GB" - ], - [ - "7b-base-q8_0", - "7.3GB" - ], - [ - "7b-chat", - "4.0GB" - ], - [ - "7b-chat-fp16", - "14GB" - ], - [ - "7b-chat-q2_K", - "3.0GB" - ], - [ - "7b-chat-q3_K_L", - "3.7GB" - ], - [ - "7b-chat-q3_K_M", - "3.5GB" - ], - [ - "7b-chat-q3_K_S", - "3.1GB" - ], - [ - "7b-chat-q4_0", - "4.0GB" - ], - [ - "7b-chat-q4_1", - "4.4GB" - ], - [ - "7b-chat-q4_K_M", - "4.2GB" - ], - [ - "7b-chat-q4_K_S", - "4.0GB" - ], - [ - "7b-chat-q5_0", - "4.8GB" - ], - [ - "7b-chat-q5_1", - "5.2GB" - ], - [ - "7b-chat-q5_K_M", - "4.9GB" - ], - [ - "7b-chat-q5_K_S", - "4.8GB" - ], - [ - "7b-chat-q6_K", - "5.7GB" - ], - [ - "7b-chat-q8_0", - "7.3GB" - ] - ], - "image": false, - "author": "DeepSeek Team" - }, "yarn-llama2": { "url": "https://ollama.com/library/yarn-llama2", "description": "An extension of Llama 2 that supports a context of up to 128k tokens.", @@ -15795,6 +15831,270 @@ "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.", + "tags": [ + [ + "latest", + "4.0GB" + ], + [ + "67b", + "38GB" + ], + [ + "7b", + "4.0GB" + ], + [ + "67b-base", + "38GB" + ], + [ + "67b-base-fp16", + "135GB" + ], + [ + "67b-base-q2_K", + "28GB" + ], + [ + "67b-base-q3_K_L", + "36GB" + ], + [ + "67b-base-q3_K_M", + "33GB" + ], + [ + "67b-base-q3_K_S", + "29GB" + ], + [ + "67b-base-q4_0", + "38GB" + ], + [ + "67b-base-q4_1", + "42GB" + ], + [ + "67b-base-q4_K_M", + "40GB" + ], + [ + "67b-base-q4_K_S", + "38GB" + ], + [ + "67b-base-q5_0", + "46GB" + ], + [ + "67b-base-q5_1", + "51GB" + ], + [ + "67b-base-q5_K_M", + "48GB" + ], + [ + "67b-base-q5_K_S", + "46GB" + ], + [ + "67b-base-q6_K", + "55GB" + ], + [ + "67b-base-q8_0", + "72GB" + ], + [ + "67b-chat", + "38GB" + ], + [ + "67b-chat-fp16", + "135GB" + ], + [ + "67b-chat-q2_K", + "28GB" + ], + [ + "67b-chat-q3_K_L", + "36GB" + ], + [ + "67b-chat-q3_K_M", + "33GB" + ], + [ + "67b-chat-q3_K_S", + "29GB" + ], + [ + "67b-chat-q4_0", + "38GB" + ], + [ + "67b-chat-q4_1", + "42GB" + ], + [ + "67b-chat-q4_K_M", + "40GB" + ], + [ + "67b-chat-q4_K_S", + "38GB" + ], + [ + "67b-chat-q5_0", + "46GB" + ], + [ + "67b-chat-q5_1", + "51GB" + ], + [ + "67b-chat-q5_K_S", + "46GB" + ], + [ + "7b-base", + "4.0GB" + ], + [ + "7b-base-fp16", + "14GB" + ], + [ + "7b-base-q2_K", + "3.0GB" + ], + [ + "7b-base-q3_K_L", + "3.7GB" + ], + [ + "7b-base-q3_K_M", + "3.5GB" + ], + [ + "7b-base-q3_K_S", + "3.1GB" + ], + [ + "7b-base-q4_0", + "4.0GB" + ], + [ + "7b-base-q4_1", + "4.4GB" + ], + [ + "7b-base-q4_K_M", + "4.2GB" + ], + [ + "7b-base-q4_K_S", + "4.0GB" + ], + [ + "7b-base-q5_0", + "4.8GB" + ], + [ + "7b-base-q5_1", + "5.2GB" + ], + [ + "7b-base-q5_K_M", + "4.9GB" + ], + [ + "7b-base-q5_K_S", + "4.8GB" + ], + [ + "7b-base-q6_K", + "5.7GB" + ], + [ + "7b-base-q8_0", + "7.3GB" + ], + [ + "7b-chat", + "4.0GB" + ], + [ + "7b-chat-fp16", + "14GB" + ], + [ + "7b-chat-q2_K", + "3.0GB" + ], + [ + "7b-chat-q3_K_L", + "3.7GB" + ], + [ + "7b-chat-q3_K_M", + "3.5GB" + ], + [ + "7b-chat-q3_K_S", + "3.1GB" + ], + [ + "7b-chat-q4_0", + "4.0GB" + ], + [ + "7b-chat-q4_1", + "4.4GB" + ], + [ + "7b-chat-q4_K_M", + "4.2GB" + ], + [ + "7b-chat-q4_K_S", + "4.0GB" + ], + [ + "7b-chat-q5_0", + "4.8GB" + ], + [ + "7b-chat-q5_1", + "5.2GB" + ], + [ + "7b-chat-q5_K_M", + "4.9GB" + ], + [ + "7b-chat-q5_K_S", + "4.8GB" + ], + [ + "7b-chat-q6_K", + "5.7GB" + ], + [ + "7b-chat-q8_0", + "7.3GB" + ] + ], + "image": false, + "author": "DeepSeek Team" + }, "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).", @@ -16083,142 +16383,6 @@ "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", - "6.1GB" - ], - [ - "10.7b", - "6.1GB" - ], - [ - "10.7b-instruct-v1-fp16", - "21GB" - ], - [ - "10.7b-instruct-v1-q2_K", - "4.5GB" - ], - [ - "10.7b-instruct-v1-q3_K_L", - "5.7GB" - ], - [ - "10.7b-instruct-v1-q3_K_M", - "5.2GB" - ], - [ - "10.7b-instruct-v1-q3_K_S", - "4.7GB" - ], - [ - "10.7b-instruct-v1-q4_0", - "6.1GB" - ], - [ - "10.7b-instruct-v1-q4_1", - "6.7GB" - ], - [ - "10.7b-instruct-v1-q4_K_M", - "6.5GB" - ], - [ - "10.7b-instruct-v1-q4_K_S", - "6.1GB" - ], - [ - "10.7b-instruct-v1-q5_0", - "7.4GB" - ], - [ - "10.7b-instruct-v1-q5_1", - "8.1GB" - ], - [ - "10.7b-instruct-v1-q5_K_M", - "7.6GB" - ], - [ - "10.7b-instruct-v1-q5_K_S", - "7.4GB" - ], - [ - "10.7b-instruct-v1-q6_K", - "8.8GB" - ], - [ - "10.7b-instruct-v1-q8_0", - "11GB" - ], - [ - "10.7b-text-v1-fp16", - "21GB" - ], - [ - "10.7b-text-v1-q2_K", - "4.5GB" - ], - [ - "10.7b-text-v1-q3_K_L", - "5.7GB" - ], - [ - "10.7b-text-v1-q3_K_M", - "5.2GB" - ], - [ - "10.7b-text-v1-q3_K_S", - "4.7GB" - ], - [ - "10.7b-text-v1-q4_0", - "6.1GB" - ], - [ - "10.7b-text-v1-q4_1", - "6.7GB" - ], - [ - "10.7b-text-v1-q4_K_M", - "6.5GB" - ], - [ - "10.7b-text-v1-q4_K_S", - "6.1GB" - ], - [ - "10.7b-text-v1-q5_0", - "7.4GB" - ], - [ - "10.7b-text-v1-q5_1", - "8.1GB" - ], - [ - "10.7b-text-v1-q5_K_M", - "7.6GB" - ], - [ - "10.7b-text-v1-q5_K_S", - "7.4GB" - ], - [ - "10.7b-text-v1-q6_K", - "8.8GB" - ], - [ - "10.7b-text-v1-q8_0", - "11GB" - ] - ], - "image": false, - "author": "Upstage" - }, "wizardlm": { "url": "https://ollama.com/library/wizardlm", "description": "General use model based on Llama 2.", @@ -16519,6 +16683,142 @@ "image": false, "author": "WizardLM Team" }, + "solar": { + "url": "https://ollama.com/library/solar", + "description": "A compact, yet powerful 10.7B large language model designed for single-turn conversation.", + "tags": [ + [ + "latest", + "6.1GB" + ], + [ + "10.7b", + "6.1GB" + ], + [ + "10.7b-instruct-v1-fp16", + "21GB" + ], + [ + "10.7b-instruct-v1-q2_K", + "4.5GB" + ], + [ + "10.7b-instruct-v1-q3_K_L", + "5.7GB" + ], + [ + "10.7b-instruct-v1-q3_K_M", + "5.2GB" + ], + [ + "10.7b-instruct-v1-q3_K_S", + "4.7GB" + ], + [ + "10.7b-instruct-v1-q4_0", + "6.1GB" + ], + [ + "10.7b-instruct-v1-q4_1", + "6.7GB" + ], + [ + "10.7b-instruct-v1-q4_K_M", + "6.5GB" + ], + [ + "10.7b-instruct-v1-q4_K_S", + "6.1GB" + ], + [ + "10.7b-instruct-v1-q5_0", + "7.4GB" + ], + [ + "10.7b-instruct-v1-q5_1", + "8.1GB" + ], + [ + "10.7b-instruct-v1-q5_K_M", + "7.6GB" + ], + [ + "10.7b-instruct-v1-q5_K_S", + "7.4GB" + ], + [ + "10.7b-instruct-v1-q6_K", + "8.8GB" + ], + [ + "10.7b-instruct-v1-q8_0", + "11GB" + ], + [ + "10.7b-text-v1-fp16", + "21GB" + ], + [ + "10.7b-text-v1-q2_K", + "4.5GB" + ], + [ + "10.7b-text-v1-q3_K_L", + "5.7GB" + ], + [ + "10.7b-text-v1-q3_K_M", + "5.2GB" + ], + [ + "10.7b-text-v1-q3_K_S", + "4.7GB" + ], + [ + "10.7b-text-v1-q4_0", + "6.1GB" + ], + [ + "10.7b-text-v1-q4_1", + "6.7GB" + ], + [ + "10.7b-text-v1-q4_K_M", + "6.5GB" + ], + [ + "10.7b-text-v1-q4_K_S", + "6.1GB" + ], + [ + "10.7b-text-v1-q5_0", + "7.4GB" + ], + [ + "10.7b-text-v1-q5_1", + "8.1GB" + ], + [ + "10.7b-text-v1-q5_K_M", + "7.6GB" + ], + [ + "10.7b-text-v1-q5_K_S", + "7.4GB" + ], + [ + "10.7b-text-v1-q6_K", + "8.8GB" + ], + [ + "10.7b-text-v1-q8_0", + "11GB" + ] + ], + "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.", @@ -17303,6 +17603,158 @@ "image": false, "author": "Snowflake" }, + "deepseek-v2": { + "url": "https://ollama.com/library/deepseek-v2", + "description": "A strong, economical, and efficient Mixture-of-Experts language model.", + "tags": [ + [ + "latest", + "8.9GB" + ], + [ + "236b", + "133GB" + ], + [ + "16b", + "8.9GB" + ], + [ + "lite", + "8.9GB" + ], + [ + "236b-chat-f16", + "472GB" + ], + [ + "236b-chat-fp16", + "472GB" + ], + [ + "236b-chat-q2_K", + "86GB" + ], + [ + "236b-chat-q3_K_L", + "122GB" + ], + [ + "236b-chat-q3_K_M", + "113GB" + ], + [ + "236b-chat-q3_K_S", + "102GB" + ], + [ + "236b-chat-q4_0", + "133GB" + ], + [ + "236b-chat-q4_1", + "148GB" + ], + [ + "236b-chat-q4_K_M", + "142GB" + ], + [ + "236b-chat-q4_K_S", + "134GB" + ], + [ + "236b-chat-q5_0", + "162GB" + ], + [ + "236b-chat-q5_1", + "177GB" + ], + [ + "236b-chat-q5_K_M", + "167GB" + ], + [ + "236b-chat-q5_K_S", + "162GB" + ], + [ + "236b-chat-q6_K", + "194GB" + ], + [ + "236b-chat-q8_0", + "251GB" + ], + [ + "16b-lite-chat-f16", + "31GB" + ], + [ + "16b-lite-chat-fp16", + "31GB" + ], + [ + "16b-lite-chat-q2_K", + "6.4GB" + ], + [ + "16b-lite-chat-q3_K_L", + "8.5GB" + ], + [ + "16b-lite-chat-q3_K_M", + "8.1GB" + ], + [ + "16b-lite-chat-q3_K_S", + "7.5GB" + ], + [ + "16b-lite-chat-q4_0", + "8.9GB" + ], + [ + "16b-lite-chat-q4_1", + "9.9GB" + ], + [ + "16b-lite-chat-q4_K_M", + "10GB" + ], + [ + "16b-lite-chat-q4_K_S", + "9.5GB" + ], + [ + "16b-lite-chat-q5_0", + "11GB" + ], + [ + "16b-lite-chat-q5_1", + "12GB" + ], + [ + "16b-lite-chat-q5_K_M", + "12GB" + ], + [ + "16b-lite-chat-q5_K_S", + "11GB" + ], + [ + "16b-lite-chat-q6_K", + "14GB" + ], + [ + "16b-lite-chat-q8_0", + "17GB" + ] + ], + "image": false, + "author": "DeepSeek Team" + }, "medllama2": { "url": "https://ollama.com/library/medllama2", "description": "Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.", @@ -17519,86 +17971,6 @@ "image": false, "author": "Nous Research" }, - "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", - "26GB" - ], - [ - "8x7b", - "26GB" - ], - [ - "dpo", - "26GB" - ], - [ - "8x7b-dpo-fp16", - "93GB" - ], - [ - "8x7b-dpo-q2_K", - "16GB" - ], - [ - "8x7b-dpo-q3_K_L", - "20GB" - ], - [ - "8x7b-dpo-q3_K_M", - "20GB" - ], - [ - "8x7b-dpo-q3_K_S", - "20GB" - ], - [ - "8x7b-dpo-q4_0", - "26GB" - ], - [ - "8x7b-dpo-q4_1", - "29GB" - ], - [ - "8x7b-dpo-q4_K_M", - "26GB" - ], - [ - "8x7b-dpo-q4_K_S", - "26GB" - ], - [ - "8x7b-dpo-q5_0", - "32GB" - ], - [ - "8x7b-dpo-q5_1", - "35GB" - ], - [ - "8x7b-dpo-q5_K_M", - "32GB" - ], - [ - "8x7b-dpo-q5_K_S", - "32GB" - ], - [ - "8x7b-dpo-q6_K", - "38GB" - ], - [ - "8x7b-dpo-q8_0", - "50GB" - ] - ], - "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.", @@ -17739,157 +18111,85 @@ "image": false, "author": "Tencent" }, - "deepseek-v2": { - "url": "https://ollama.com/library/deepseek-v2", - "description": "A strong, economical, and efficient Mixture-of-Experts language model.", + "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", - "8.9GB" + "26GB" ], [ - "236b", - "133GB" + "8x7b", + "26GB" ], [ - "16b", - "8.9GB" + "dpo", + "26GB" ], [ - "lite", - "8.9GB" + "8x7b-dpo-fp16", + "93GB" ], [ - "236b-chat-f16", - "472GB" + "8x7b-dpo-q2_K", + "16GB" ], [ - "236b-chat-fp16", - "472GB" + "8x7b-dpo-q3_K_L", + "20GB" ], [ - "236b-chat-q2_K", - "86GB" + "8x7b-dpo-q3_K_M", + "20GB" ], [ - "236b-chat-q3_K_L", - "122GB" + "8x7b-dpo-q3_K_S", + "20GB" ], [ - "236b-chat-q3_K_M", - "113GB" + "8x7b-dpo-q4_0", + "26GB" ], [ - "236b-chat-q3_K_S", - "102GB" + "8x7b-dpo-q4_1", + "29GB" ], [ - "236b-chat-q4_0", - "133GB" + "8x7b-dpo-q4_K_M", + "26GB" ], [ - "236b-chat-q4_1", - "148GB" + "8x7b-dpo-q4_K_S", + "26GB" ], [ - "236b-chat-q4_K_M", - "142GB" + "8x7b-dpo-q5_0", + "32GB" ], [ - "236b-chat-q4_K_S", - "134GB" + "8x7b-dpo-q5_1", + "35GB" ], [ - "236b-chat-q5_0", - "162GB" + "8x7b-dpo-q5_K_M", + "32GB" ], [ - "236b-chat-q5_1", - "177GB" + "8x7b-dpo-q5_K_S", + "32GB" ], [ - "236b-chat-q5_K_M", - "167GB" + "8x7b-dpo-q6_K", + "38GB" ], [ - "236b-chat-q5_K_S", - "162GB" - ], - [ - "236b-chat-q6_K", - "194GB" - ], - [ - "236b-chat-q8_0", - "251GB" - ], - [ - "16b-lite-chat-f16", - "31GB" - ], - [ - "16b-lite-chat-fp16", - "31GB" - ], - [ - "16b-lite-chat-q2_K", - "6.4GB" - ], - [ - "16b-lite-chat-q3_K_L", - "8.5GB" - ], - [ - "16b-lite-chat-q3_K_M", - "8.1GB" - ], - [ - "16b-lite-chat-q3_K_S", - "7.5GB" - ], - [ - "16b-lite-chat-q4_0", - "8.9GB" - ], - [ - "16b-lite-chat-q4_1", - "9.9GB" - ], - [ - "16b-lite-chat-q4_K_M", - "10GB" - ], - [ - "16b-lite-chat-q4_K_S", - "9.5GB" - ], - [ - "16b-lite-chat-q5_0", - "11GB" - ], - [ - "16b-lite-chat-q5_1", - "12GB" - ], - [ - "16b-lite-chat-q5_K_M", - "12GB" - ], - [ - "16b-lite-chat-q5_K_S", - "11GB" - ], - [ - "16b-lite-chat-q6_K", - "14GB" - ], - [ - "16b-lite-chat-q8_0", - "17GB" + "8x7b-dpo-q8_0", + "50GB" ] ], "image": false, - "author": "DeepSeek Team" + "author": "Nous Research" }, "meditron": { "url": "https://ollama.com/library/meditron", @@ -18000,11 +18300,11 @@ "7.4GB" ], [ - "13b-llama2", + "13b-llama2-chat", "7.4GB" ], [ - "13b-llama2-chat", + "13b-llama2", "7.4GB" ], [ @@ -18311,6 +18611,218 @@ "image": false, "author": "Xtuner" }, + "codegeex4": { + "url": "https://ollama.com/library/codegeex4", + "description": "A versatile model for AI software development scenarios, including code completion.", + "tags": [ + [ + "latest", + "5.5GB" + ], + [ + "9b", + "5.5GB" + ], + [ + "9b-all-fp16", + "19GB" + ], + [ + "9b-all-q2_K", + "4.0GB" + ], + [ + "9b-all-q3_K_L", + "5.3GB" + ], + [ + "9b-all-q3_K_M", + "5.1GB" + ], + [ + "9b-all-q3_K_S", + "4.6GB" + ], + [ + "9b-all-q4_0", + "5.5GB" + ], + [ + "9b-all-q4_1", + "6.0GB" + ], + [ + "9b-all-q4_K_M", + "6.3GB" + ], + [ + "9b-all-q4_K_S", + "5.8GB" + ], + [ + "9b-all-q5_0", + "6.6GB" + ], + [ + "9b-all-q5_1", + "7.1GB" + ], + [ + "9b-all-q5_K_M", + "7.1GB" + ], + [ + "9b-all-q5_K_S", + "6.7GB" + ], + [ + "9b-all-q6_K", + "8.3GB" + ], + [ + "9b-all-q8_0", + "10.0GB" + ] + ], + "image": false, + "author": "THUDM" + }, + "glm4": { + "url": "https://ollama.com/library/glm4", + "description": "A strong multi-lingual general language model with competitive performance to Llama 3.", + "tags": [ + [ + "latest", + "5.5GB" + ], + [ + "9b", + "5.5GB" + ], + [ + "9b-chat-fp16", + "19GB" + ], + [ + "9b-chat-q2_K", + "4.0GB" + ], + [ + "9b-chat-q3_K_L", + "5.3GB" + ], + [ + "9b-chat-q3_K_M", + "5.1GB" + ], + [ + "9b-chat-q3_K_S", + "4.6GB" + ], + [ + "9b-chat-q4_0", + "5.5GB" + ], + [ + "9b-chat-q4_1", + "6.0GB" + ], + [ + "9b-chat-q4_K_M", + "6.3GB" + ], + [ + "9b-chat-q4_K_S", + "5.8GB" + ], + [ + "9b-chat-q5_0", + "6.6GB" + ], + [ + "9b-chat-q5_1", + "7.1GB" + ], + [ + "9b-chat-q5_K_M", + "7.1GB" + ], + [ + "9b-chat-q5_K_S", + "6.7GB" + ], + [ + "9b-chat-q6_K", + "8.3GB" + ], + [ + "9b-chat-q8_0", + "10.0GB" + ], + [ + "9b-text-fp16", + "19GB" + ], + [ + "9b-text-q2_K", + "4.0GB" + ], + [ + "9b-text-q3_K_L", + "5.3GB" + ], + [ + "9b-text-q3_K_M", + "5.1GB" + ], + [ + "9b-text-q3_K_S", + "4.6GB" + ], + [ + "9b-text-q4_0", + "5.5GB" + ], + [ + "9b-text-q4_1", + "6.0GB" + ], + [ + "9b-text-q4_K_M", + "6.3GB" + ], + [ + "9b-text-q4_K_S", + "5.8GB" + ], + [ + "9b-text-q5_0", + "6.6GB" + ], + [ + "9b-text-q5_1", + "7.1GB" + ], + [ + "9b-text-q5_K_M", + "7.1GB" + ], + [ + "9b-text-q5_K_S", + "6.7GB" + ], + [ + "9b-text-q6_K", + "8.3GB" + ], + [ + "9b-text-q8_0", + "10.0GB" + ] + ], + "image": false, + "author": "THUDM" + }, "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.", @@ -18615,273 +19127,77 @@ "image": false, "author": "Amazon Web Services" }, - "glm4": { - "url": "https://ollama.com/library/glm4", - "description": "A strong multi-lingual general language model with competitive performance to Llama 3.", - "tags": [ - [ - "latest", - "5.5GB" - ], - [ - "9b", - "5.5GB" - ], - [ - "9b-chat-fp16", - "19GB" - ], - [ - "9b-chat-q2_K", - "4.0GB" - ], - [ - "9b-chat-q3_K_L", - "5.3GB" - ], - [ - "9b-chat-q3_K_M", - "5.1GB" - ], - [ - "9b-chat-q3_K_S", - "4.6GB" - ], - [ - "9b-chat-q4_0", - "5.5GB" - ], - [ - "9b-chat-q4_1", - "6.0GB" - ], - [ - "9b-chat-q4_K_M", - "6.3GB" - ], - [ - "9b-chat-q4_K_S", - "5.8GB" - ], - [ - "9b-chat-q5_0", - "6.6GB" - ], - [ - "9b-chat-q5_1", - "7.1GB" - ], - [ - "9b-chat-q5_K_M", - "7.1GB" - ], - [ - "9b-chat-q5_K_S", - "6.7GB" - ], - [ - "9b-chat-q6_K", - "8.3GB" - ], - [ - "9b-chat-q8_0", - "10.0GB" - ], - [ - "9b-text-fp16", - "19GB" - ], - [ - "9b-text-q2_K", - "4.0GB" - ], - [ - "9b-text-q3_K_L", - "5.3GB" - ], - [ - "9b-text-q3_K_M", - "5.1GB" - ], - [ - "9b-text-q3_K_S", - "4.6GB" - ], - [ - "9b-text-q4_0", - "5.5GB" - ], - [ - "9b-text-q4_1", - "6.0GB" - ], - [ - "9b-text-q4_K_M", - "6.3GB" - ], - [ - "9b-text-q4_K_S", - "5.8GB" - ], - [ - "9b-text-q5_0", - "6.6GB" - ], - [ - "9b-text-q5_1", - "7.1GB" - ], - [ - "9b-text-q5_K_M", - "7.1GB" - ], - [ - "9b-text-q5_K_S", - "6.7GB" - ], - [ - "9b-text-q6_K", - "8.3GB" - ], - [ - "9b-text-q8_0", - "10.0GB" - ] - ], - "image": false, - "author": "THUDM" - }, "wizard-vicuna": { "url": "https://ollama.com/library/wizard-vicuna", - "description": "A strong multi-lingual general language model with competitive performance to Llama 3.", + "description": "Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.", "tags": [ [ "latest", - "5.5GB" + "7.4GB" ], [ - "9b", - "5.5GB" + "13b", + "7.4GB" ], [ - "9b-chat-fp16", - "19GB" + "13b-fp16", + "26GB" ], [ - "9b-chat-q2_K", - "4.0GB" + "13b-q2_K", + "5.4GB" ], [ - "9b-chat-q3_K_L", - "5.3GB" + "13b-q3_K_L", + "6.9GB" ], [ - "9b-chat-q3_K_M", - "5.1GB" - ], - [ - "9b-chat-q3_K_S", - "4.6GB" - ], - [ - "9b-chat-q4_0", - "5.5GB" - ], - [ - "9b-chat-q4_1", - "6.0GB" - ], - [ - "9b-chat-q4_K_M", + "13b-q3_K_M", "6.3GB" ], [ - "9b-chat-q4_K_S", - "5.8GB" + "13b-q3_K_S", + "5.7GB" ], [ - "9b-chat-q5_0", - "6.6GB" + "13b-q4_0", + "7.4GB" ], [ - "9b-chat-q5_1", - "7.1GB" + "13b-q4_1", + "8.2GB" ], [ - "9b-chat-q5_K_M", - "7.1GB" + "13b-q4_K_M", + "7.9GB" ], [ - "9b-chat-q5_K_S", - "6.7GB" + "13b-q4_K_S", + "7.4GB" ], [ - "9b-chat-q6_K", - "8.3GB" + "13b-q5_0", + "9.0GB" ], [ - "9b-chat-q8_0", - "10.0GB" + "13b-q5_1", + "9.8GB" ], [ - "9b-text-fp16", - "19GB" + "13b-q5_K_M", + "9.2GB" ], [ - "9b-text-q2_K", - "4.0GB" + "13b-q5_K_S", + "9.0GB" ], [ - "9b-text-q3_K_L", - "5.3GB" + "13b-q6_K", + "11GB" ], [ - "9b-text-q3_K_M", - "5.1GB" - ], - [ - "9b-text-q3_K_S", - "4.6GB" - ], - [ - "9b-text-q4_0", - "5.5GB" - ], - [ - "9b-text-q4_1", - "6.0GB" - ], - [ - "9b-text-q4_K_M", - "6.3GB" - ], - [ - "9b-text-q4_K_S", - "5.8GB" - ], - [ - "9b-text-q5_0", - "6.6GB" - ], - [ - "9b-text-q5_1", - "7.1GB" - ], - [ - "9b-text-q5_K_M", - "7.1GB" - ], - [ - "9b-text-q5_K_S", - "6.7GB" - ], - [ - "9b-text-q6_K", - "8.3GB" - ], - [ - "9b-text-q8_0", - "10.0GB" + "13b-q8_0", + "14GB" ] ], "image": false, @@ -19467,118 +19783,6 @@ "image": false, "author": "Databricks" }, - "codegeex4": { - "url": "https://ollama.com/library/codegeex4", - "description": "A versatile model for AI software development scenarios, including code completion.", - "tags": [ - [ - "latest", - "5.5GB" - ], - [ - "9b", - "5.5GB" - ], - [ - "9b-all-fp16", - "19GB" - ], - [ - "9b-all-q2_K", - "4.0GB" - ], - [ - "9b-all-q3_K_L", - "5.3GB" - ], - [ - "9b-all-q3_K_M", - "5.1GB" - ], - [ - "9b-all-q3_K_S", - "4.6GB" - ], - [ - "9b-all-q4_0", - "5.5GB" - ], - [ - "9b-all-q4_1", - "6.0GB" - ], - [ - "9b-all-q4_K_M", - "6.3GB" - ], - [ - "9b-all-q4_K_S", - "5.8GB" - ], - [ - "9b-all-q5_0", - "6.6GB" - ], - [ - "9b-all-q5_1", - "7.1GB" - ], - [ - "9b-all-q5_K_M", - "7.1GB" - ], - [ - "9b-all-q5_K_S", - "6.7GB" - ], - [ - "9b-all-q6_K", - "8.3GB" - ], - [ - "9b-all-q8_0", - "10.0GB" - ] - ], - "image": false, - "author": "THUDM" - }, - "alfred": { - "url": "https://ollama.com/library/alfred", - "description": "A robust conversational model designed to be used for both chat and instruct use cases.", - "tags": [ - [ - "latest", - "24GB" - ], - [ - "40b", - "24GB" - ], - [ - "40b-1023-q4_0", - "24GB" - ], - [ - "40b-1023-q4_1", - "26GB" - ], - [ - "40b-1023-q5_0", - "29GB" - ], - [ - "40b-1023-q5_1", - "32GB" - ], - [ - "40b-1023-q8_0", - "44GB" - ] - ], - "image": false, - "author": "LightOn AI" - }, "internlm2": { "url": "https://ollama.com/library/internlm2", "description": "InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability.", @@ -19653,7 +19857,43 @@ ] ], "image": false, - "author": "InternLM" + "author": "Intern LM" + }, + "alfred": { + "url": "https://ollama.com/library/alfred", + "description": "A robust conversational model designed to be used for both chat and instruct use cases.", + "tags": [ + [ + "latest", + "24GB" + ], + [ + "40b", + "24GB" + ], + [ + "40b-1023-q4_0", + "24GB" + ], + [ + "40b-1023-q4_1", + "26GB" + ], + [ + "40b-1023-q5_0", + "29GB" + ], + [ + "40b-1023-q5_1", + "32GB" + ], + [ + "40b-1023-q8_0", + "44GB" + ] + ], + "image": false, + "author": "LightOn AI" }, "llama3-groq-tool-use": { "url": "https://ollama.com/library/llama3-groq-tool-use", @@ -19793,7 +20033,7 @@ ] ], "image": false, - "author": "Groq Inc" + "author": "Groq" }, "mathstral": { "url": "https://ollama.com/library/mathstral", @@ -19871,82 +20111,6 @@ "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", - "7.1GB" - ], - [ - "12b", - "7.1GB" - ], - [ - "12b-instruct-2407-fp16", - "25GB" - ], - [ - "12b-instruct-2407-q2_K", - "4.8GB" - ], - [ - "12b-instruct-2407-q3_K_L", - "6.6GB" - ], - [ - "12b-instruct-2407-q3_K_M", - "6.1GB" - ], - [ - "12b-instruct-2407-q3_K_S", - "5.5GB" - ], - [ - "12b-instruct-2407-q4_0", - "7.1GB" - ], - [ - "12b-instruct-2407-q4_1", - "7.8GB" - ], - [ - "12b-instruct-2407-q4_K_M", - "7.5GB" - ], - [ - "12b-instruct-2407-q4_K_S", - "7.1GB" - ], - [ - "12b-instruct-2407-q5_0", - "8.5GB" - ], - [ - "12b-instruct-2407-q5_1", - "9.2GB" - ], - [ - "12b-instruct-2407-q5_K_M", - "8.7GB" - ], - [ - "12b-instruct-2407-q5_K_S", - "8.5GB" - ], - [ - "12b-instruct-2407-q6_K", - "10GB" - ], - [ - "12b-instruct-2407-q8_0", - "13GB" - ] - ], - "image": false, - "author": "Mistral AI" - }, "firefunction-v2": { "url": "https://ollama.com/library/firefunction-v2", "description": "An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.", @@ -20097,6 +20261,6 @@ ] ], "image": false, - "author": "NuMind" + "author": "Numind" } } \ No newline at end of file diff --git a/src/available_models_descriptions.py b/src/available_models_descriptions.py index 4069b31..353c011 100644 --- a/src/available_models_descriptions.py +++ b/src/available_models_descriptions.py @@ -1,16 +1,18 @@ 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 now available in 2 sizes, 9B and 27B."), - 'llama3': _("Meta Llama 3: The most capable openly available LLM to date"), + '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."), - 'aya': _("Aya 23, released by Cohere, is a new family of state-of-the-art, multilingual models that support 23 languages."), '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."), 'command-r': _("Command R is a Large Language Model optimized for conversational interaction and long context tasks."), 'command-r-plus': _("Command R+ is a powerful, scalable large language model purpose-built to excel at real-world enterprise use cases."), 'llava': _("🌋 LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding. Updated to version 1.6."), + '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"), 'llama2': _("Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters."), @@ -18,49 +20,50 @@ descriptions = { 'dolphin-mixtral': _("Uncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford."), 'nomic-embed-text': _("A high-performing open embedding model with a large token context window."), '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."), 'phi': _("Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities."), + 'deepseek-coder': _("DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens."), 'dolphin-mistral': _("The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8."), 'orca-mini': _("A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware."), '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."), 'mxbai-embed-large': _("State-of-the-art large embedding model from mixedbread.ai"), - 'mistral-openorca': _("Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset."), 'starcoder2': _("StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters."), - 'zephyr': _("Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants."), + 'mistral-openorca': _("Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset."), 'yi': _("Yi 1.5 is a high-performing, bilingual language model."), + 'zephyr': _("Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants."), 'llama2-chinese': _("Llama 2 based model fine tuned to improve Chinese dialogue ability."), 'llava-llama3': _("A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks."), 'vicuna': _("General use chat model based on Llama and Llama 2 with 2K to 16K context sizes."), 'nous-hermes2': _("The powerful family of models by Nous Research that excels at scientific discussion and coding tasks."), - 'wizard-vicuna-uncensored': _("Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford."), 'tinyllama': _("The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens."), + 'wizard-vicuna-uncensored': _("Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford."), 'codestral': _("Codestral is Mistral AI’s first-ever code model designed for code generation tasks."), 'starcoder': _("StarCoder is a code generation model trained on 80+ programming languages."), 'wizardlm2': _("State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases."), '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."), 'tinydolphin': _("An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama."), 'openhermes': _("OpenHermes 2.5 is a 7B model fine-tuned by Teknium on Mistral with fully open 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."), 'codeqwen': _("CodeQwen1.5 is a large language model pretrained on a large amount of code data."), - 'neural-chat': _("A fine-tuned model based on Mistral with good coverage of domain and language."), '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."), '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."), - 'all-minilm': _("Embedding models on very large sentence level datasets."), 'granite-code': _("A family of open foundation models by IBM for Code Intelligence"), + 'all-minilm': _("Embedding models on very large sentence level datasets."), 'phind-codellama': _("Code generation model based on Code Llama."), 'dolphincoder': _("A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2."), 'nous-hermes': _("General use models based on Llama and Llama 2 from Nous Research."), 'sqlcoder': _("SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks"), 'llama3-gradient': _("This model extends LLama-3 8B's context length from 8k to over 1m tokens."), 'starling-lm': _("Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness."), - '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."), '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."), 'llama3-chatqa': _("A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG)."), '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."), 'wizardlm': _("General use model based on Llama 2."), + '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."), 'dolphin-phi': _("2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research."), 'stable-beluga': _("Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy."), @@ -68,22 +71,23 @@ descriptions = { 'bakllava': _("BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture."), 'wizardlm-uncensored': _("Uncensored version of Wizard LM model"), 'snowflake-arctic-embed': _("A suite of text embedding models by Snowflake, optimized for performance."), + 'deepseek-v2': _("A strong, economical, and efficient Mixture-of-Experts language model."), 'medllama2': _("Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset."), 'yarn-mistral': _("An extension of Mistral to support context windows of 64K or 128K."), - 'nous-hermes2-mixtral': _("The Nous Hermes 2 model from Nous Research, now trained over Mixtral."), 'llama-pro': _("An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics."), - 'deepseek-v2': _("A strong, economical, and efficient Mixture-of-Experts language model."), + 'nous-hermes2-mixtral': _("The Nous Hermes 2 model from Nous Research, now trained over Mixtral."), 'meditron': _("Open-source medical large language model adapted from Llama 2 to the medical domain."), 'codeup': _("Great code generation model based on Llama2."), 'nexusraven': _("Nexus Raven is a 13B instruction tuned model for function calling tasks."), 'everythinglm': _("Uncensored Llama2 based model with support for a 16K context window."), 'llava-phi3': _("A new small LLaVA model fine-tuned from Phi 3 Mini."), + 'codegeex4': _("A versatile model for AI software development scenarios, including code completion."), + 'glm4': _("A strong multi-lingual general language model with competitive performance to Llama 3."), '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."), - 'glm4': _("A strong multi-lingual general language model with competitive performance to Llama 3."), - 'wizard-vicuna': _("A strong multi-lingual general language model with competitive performance to Llama 3."), + '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."), 'megadolphin': _("MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself."), 'goliath': _("A language model created by combining two fine-tuned Llama 2 70B models into one."), @@ -92,12 +96,10 @@ descriptions = { 'falcon2': _("Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens."), '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."), - 'codegeex4': _("A versatile model for AI software development scenarios, including code completion."), - 'alfred': _("A robust conversational model designed to be used for both chat and instruct use cases."), 'internlm2': _("InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability."), + 'alfred': _("A robust conversational model designed to be used for both chat and instruct use cases."), '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."), 'mathstral': _("MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI."), - 'mistral-nemo': _("A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA."), '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."), } \ No newline at end of file