evandro/OllaHub
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: address issues in model pull and chat API

Browse Source 
- Refactored model pull logic to improve error handling and user feedback.
- Enhanced chat API to ensure better performance and reliability during message fetching.
- Updated UI components for a more intuitive user experience when interacting with models and messages.
This commit is contained in:
Evandro Fonseca Junior committed 2025-11-19 00:01:14 -03:00
1 parent ad9d5d32d2
commit b2a06ed994
261 files changed
+19968
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

data/models/alfred.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "alfred",
"url": "https://ollama.com/library/alfred",
"description": "A robust conversational model designed to be used for both chat and instruct use cases.",
"variantsCount": 2,
"variants": [
{
"name": "alfred:latest",
"size": "24GB",
"context": "2K",
"inputType": "Text"
},
{
"name": "alfred:40b",
"size": "24GB",
"context": "2K",
"inputType": "Text"
}
]
}
data/models/all-minilm.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "all-minilm",
"url": "https://ollama.com/library/all-minilm",
"description": "Embedding models on very large sentence level datasets.",
"variantsCount": 3,
"variants": [
{
"name": "all-minilm:latest",
"size": "46MB",
"context": "512",
"inputType": "Text"
},
{
"name": "all-minilm:22m",
"size": "46MB",
"context": "512",
"inputType": "Text"
},
{
"name": "all-minilm:33m",
"size": "67MB",
"context": "512",
"inputType": "Text"
}
]
}
data/models/athene-v2.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "athene-v2",
"url": "https://ollama.com/library/athene-v2",
"description": "Athene-V2 is a 72B parameter model which excels at code completion, mathematics, and log extraction tasks.",
"variantsCount": 2,
"variants": [
{
"name": "athene-v2:latest",
"size": "47GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "athene-v2:72b",
"size": "47GB",
"context": "32K",
"inputType": "Text"
}
]
}
data/models/aya-expanse.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "aya-expanse",
"url": "https://ollama.com/library/aya-expanse",
"description": "Cohere For AI's language models trained to perform well across 23 different languages.",
"variantsCount": 3,
"variants": [
{
"name": "aya-expanse:latest",
"size": "5.1GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "aya-expanse:8b",
"size": "5.1GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "aya-expanse:32b",
"size": "20GB",
"context": "8K",
"inputType": "Text"
}
]
}
data/models/aya.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "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. ",
"variantsCount": 3,
"variants": [
{
"name": "aya:latest",
"size": "4.8GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "aya:8b",
"size": "4.8GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "aya:35b",
"size": "20GB",
"context": "8K",
"inputType": "Text"
}
]
}
data/models/bakllava.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "bakllava",
"url": "https://ollama.com/library/bakllava",
"description": "BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.",
"variantsCount": 2,
"variants": [
{
"name": "bakllava:latest",
"size": "4.7GB",
"context": "32K",
"inputType": "Text, Image"
},
{
"name": "bakllava:7b",
"size": "4.7GB",
"context": "32K",
"inputType": "Text, Image"
}
]
}
data/models/bespoke-minicheck.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "bespoke-minicheck",
"url": "https://ollama.com/library/bespoke-minicheck",
"description": "A state-of-the-art fact-checking model developed by Bespoke Labs.",
"variantsCount": 2,
"variants": [
{
"name": "bespoke-minicheck:latest",
"size": "4.7GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "bespoke-minicheck:7b",
"size": "4.7GB",
"context": "32K",
"inputType": "Text"
}
]
}
data/models/bge-large.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "bge-large",
"url": "https://ollama.com/library/bge-large",
"description": "Embedding model from BAAI mapping texts to vectors.",
"variantsCount": 2,
"variants": [
{
"name": "bge-large:latest",
"size": "671MB",
"context": "512",
"inputType": "Text"
},
{
"name": "bge-large:335m",
"size": "671MB",
"context": "512",
"inputType": "Text"
}
]
}
data/models/bge-m3.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "bge-m3",
"url": "https://ollama.com/library/bge-m3",
"description": "BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.",
"variantsCount": 2,
"variants": [
{
"name": "bge-m3:latest",
"size": "1.2GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "bge-m3:567m",
"size": "1.2GB",
"context": "8K",
"inputType": "Text"
}
]
}
data/models/codebooga.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "codebooga",
"url": "https://ollama.com/library/codebooga",
"description": "A high-performing code instruct model created by merging two existing code models.",
"variantsCount": 2,
"variants": [
{
"name": "codebooga:latest",
"size": "19GB",
"context": "16K",
"inputType": "Text"
},
{
"name": "codebooga:34b",
"size": "19GB",
"context": "16K",
"inputType": "Text"
}
]
}
data/models/codegeex4.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "codegeex4",
"url": "https://ollama.com/library/codegeex4",
"description": "A versatile model for AI software development scenarios, including code completion.",
"variantsCount": 2,
"variants": [
{
"name": "codegeex4:latest",
"size": "5.5GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "codegeex4:9b",
"size": "5.5GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/codegemma.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "codegemma",
"url": "https://ollama.com/library/codegemma",
"description": "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.",
"variantsCount": 3,
"variants": [
{
"name": "codegemma:latest",
"size": "5.0GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "codegemma:2b",
"size": "1.6GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "codegemma:7b",
"size": "5.0GB",
"context": "8K",
"inputType": "Text"
}
]
}
data/models/codellama.json
+38
View File
@@ -0,0 +1,38 @@
{
"model": "codellama",
"url": "https://ollama.com/library/codellama",
"description": "A large language model that can use text prompts to generate and discuss code.",
"variantsCount": 5,
"variants": [
{
"name": "codellama:latest",
"size": "3.8GB",
"context": "16K",
"inputType": "Text"
},
{
"name": "codellama:7b",
"size": "3.8GB",
"context": "16K",
"inputType": "Text"
},
{
"name": "codellama:13b",
"size": "7.4GB",
"context": "16K",
"inputType": "Text"
},
{
"name": "codellama:34b",
"size": "19GB",
"context": "16K",
"inputType": "Text"
},
{
"name": "codellama:70b",
"size": "39GB",
"context": "2K",
"inputType": "Text"
}
]
}
data/models/codeqwen.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "codeqwen",
"url": "https://ollama.com/library/codeqwen",
"description": "CodeQwen1.5 is a large language model pretrained on a large amount of code data.",
"variantsCount": 2,
"variants": [
{
"name": "codeqwen:latest",
"size": "4.2GB",
"context": "64K",
"inputType": "Text"
},
{
"name": "codeqwen:7b",
"size": "4.2GB",
"context": "64K",
"inputType": "Text"
}
]
}
data/models/codestral.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "codestral",
"url": "https://ollama.com/library/codestral",
"description": "Codestral is Mistral AI’s first-ever code model designed for code generation tasks.",
"variantsCount": 2,
"variants": [
{
"name": "codestral:latest",
"size": "13GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "codestral:22b",
"size": "13GB",
"context": "32K",
"inputType": "Text"
}
]
}
data/models/codeup.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "codeup",
"url": "https://ollama.com/library/codeup",
"description": "Great code generation model based on Llama2.",
"variantsCount": 2,
"variants": [
{
"name": "codeup:latest",
"size": "7.4GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "codeup:13b",
"size": "7.4GB",
"context": "4K",
"inputType": "Text"
}
]
}
data/models/cogito.json
+44
View File
@@ -0,0 +1,44 @@
{
"model": "cogito",
"url": "https://ollama.com/library/cogito",
"description": "Cogito v1 Preview is a family of hybrid reasoning models by Deep Cogito that outperform the best available open models of the same size, including counterparts from LLaMA, DeepSeek, and Qwen across most standard benchmarks.",
"variantsCount": 6,
"variants": [
{
"name": "cogito:latest",
"size": "4.9GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "cogito:3b",
"size": "2.2GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "cogito:8b",
"size": "4.9GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "cogito:14b",
"size": "9.0GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "cogito:32b",
"size": "20GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "cogito:70b",
"size": "43GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/command-a.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "command-a",
"url": "https://ollama.com/library/command-a",
"description": "111 billion parameter model optimized for demanding enterprises that require fast, secure, and high-quality AI",
"variantsCount": 2,
"variants": [
{
"name": "command-a:latest",
"size": "67GB",
"context": "16K",
"inputType": "Text"
},
{
"name": "command-a:111b",
"size": "67GB",
"context": "16K",
"inputType": "Text"
}
]
}
data/models/command-r-plus.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "command-r-plus",
"url": "https://ollama.com/library/command-r-plus",
"description": "Command R+ is a powerful, scalable large language model purpose-built to excel at real-world enterprise use cases.",
"variantsCount": 2,
"variants": [
{
"name": "command-r-plus:latest",
"size": "59GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "command-r-plus:104b",
"size": "59GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/command-r.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "command-r",
"url": "https://ollama.com/library/command-r",
"description": "Command R is a Large Language Model optimized for conversational interaction and long context tasks.",
"variantsCount": 2,
"variants": [
{
"name": "command-r:latest",
"size": "19GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "command-r:35b",
"size": "19GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/command-r7b-arabic.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "command-r7b-arabic",
"url": "https://ollama.com/library/command-r7b-arabic",
"description": "A new state-of-the-art version of the lightweight Command R7B model that excels in advanced Arabic language capabilities for enterprises in the Middle East and Northern Africa.",
"variantsCount": 2,
"variants": [
{
"name": "command-r7b-arabic:latest",
"size": "5.1GB",
"context": "16K",
"inputType": "Text"
},
{
"name": "command-r7b-arabic:7b",
"size": "5.1GB",
"context": "16K",
"inputType": "Text"
}
]
}
data/models/command-r7b.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "command-r7b",
"url": "https://ollama.com/library/command-r7b",
"description": "The smallest model in Cohere's R series delivers top-tier speed, efficiency, and quality to build powerful AI applications on commodity GPUs and edge devices.",
"variantsCount": 2,
"variants": [
{
"name": "command-r7b:latest",
"size": "5.1GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "command-r7b:7b",
"size": "5.1GB",
"context": "8K",
"inputType": "Text"
}
]
}
data/models/dbrx.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "dbrx",
"url": "https://ollama.com/library/dbrx",
"description": "DBRX is an open, general-purpose LLM created by Databricks.",
"variantsCount": 2,
"variants": [
{
"name": "dbrx:latest",
"size": "74GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "dbrx:132b",
"size": "74GB",
"context": "32K",
"inputType": "Text"
}
]
}
data/models/deepcoder.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "deepcoder",
"url": "https://ollama.com/library/deepcoder",
"description": "DeepCoder is a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.",
"variantsCount": 3,
"variants": [
{
"name": "deepcoder:latest",
"size": "9.0GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "deepcoder:1.5b",
"size": "1.1GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "deepcoder:14b",
"size": "9.0GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/deepscaler.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "deepscaler",
"url": "https://ollama.com/library/deepscaler",
"description": "A fine-tuned version of Deepseek-R1-Distilled-Qwen-1.5B that surpasses the performance of OpenAI’s o1-preview with just 1.5B parameters on popular math evaluations.",
"variantsCount": 2,
"variants": [
{
"name": "deepscaler:latest",
"size": "3.6GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "deepscaler:1.5b",
"size": "3.6GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/deepseek-coder-v2.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "deepseek-coder-v2",
"url": "https://ollama.com/library/deepseek-coder-v2",
"description": "An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.",
"variantsCount": 3,
"variants": [
{
"name": "deepseek-coder-v2:latest",
"size": "8.9GB",
"context": "160K",
"inputType": "Text"
},
{
"name": "deepseek-coder-v2:16b",
"size": "8.9GB",
"context": "160K",
"inputType": "Text"
},
{
"name": "deepseek-coder-v2:236b",
"size": "133GB",
"context": "4K",
"inputType": "Text"
}
]
}
data/models/deepseek-coder.json
+32
View File
@@ -0,0 +1,32 @@
{
"model": "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.",
"variantsCount": 4,
"variants": [
{
"name": "deepseek-coder:latest",
"size": "776MB",
"context": "16K",
"inputType": "Text"
},
{
"name": "deepseek-coder:1.3b",
"size": "776MB",
"context": "16K",
"inputType": "Text"
},
{
"name": "deepseek-coder:6.7b",
"size": "3.8GB",
"context": "16K",
"inputType": "Text"
},
{
"name": "deepseek-coder:33b",
"size": "19GB",
"context": "16K",
"inputType": "Text"
}
]
}
data/models/deepseek-llm.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "deepseek-llm",
"url": "https://ollama.com/library/deepseek-llm",
"description": "An advanced language model crafted with 2 trillion bilingual tokens.",
"variantsCount": 3,
"variants": [
{
"name": "deepseek-llm:latest",
"size": "4.0GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "deepseek-llm:7b",
"size": "4.0GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "deepseek-llm:67b",
"size": "38GB",
"context": "4K",
"inputType": "Text"
}
]
}
data/models/deepseek-r1.json
+56
View File
@@ -0,0 +1,56 @@
{
"model": "deepseek-r1",
"url": "https://ollama.com/library/deepseek-r1",
"description": "DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.",
"variantsCount": 8,
"variants": [
{
"name": "deepseek-r1:latest",
"size": "5.2GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "deepseek-r1:1.5b",
"size": "1.1GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "deepseek-r1:7b",
"size": "4.7GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "deepseek-r1:8b",
"size": "5.2GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "deepseek-r1:14b",
"size": "9.0GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "deepseek-r1:32b",
"size": "20GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "deepseek-r1:70b",
"size": "43GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "deepseek-r1:671b",
"size": "404GB",
"context": "160K",
"inputType": "Text"
}
]
}
data/models/deepseek-v2.5.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "deepseek-v2.5",
"url": "https://ollama.com/library/deepseek-v2.5",
"description": "An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.",
"variantsCount": 2,
"variants": [
{
"name": "deepseek-v2.5:latest",
"size": "133GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "deepseek-v2.5:236b",
"size": "133GB",
"context": "4K",
"inputType": "Text"
}
]
}
data/models/deepseek-v2.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "deepseek-v2",
"url": "https://ollama.com/library/deepseek-v2",
"description": "A strong, economical, and efficient Mixture-of-Experts language model.",
"variantsCount": 3,
"variants": [
{
"name": "deepseek-v2:latest",
"size": "8.9GB",
"context": "160K",
"inputType": "Text"
},
{
"name": "deepseek-v2:16b",
"size": "8.9GB",
"context": "160K",
"inputType": "Text"
},
{
"name": "deepseek-v2:236b",
"size": "133GB",
"context": "4K",
"inputType": "Text"
}
]
}
data/models/deepseek-v3.1.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "deepseek-v3.1",
"url": "https://ollama.com/library/deepseek-v3.1",
"description": "DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.",
"variantsCount": 3,
"variants": [
{
"name": "deepseek-v3.1:latest",
"size": "404GB",
"context": "160K",
"inputType": "Text"
},
{
"name": "deepseek-v3.1:671b",
"size": "404GB",
"context": "160K",
"inputType": "Text"
},
{
"name": "deepseek-v3.1:671b-cloud",
"size": "-",
"context": "160K",
"inputType": "Text"
}
]
}
data/models/deepseek-v3.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "deepseek-v3",
"url": "https://ollama.com/library/deepseek-v3",
"description": "A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.",
"variantsCount": 2,
"variants": [
{
"name": "deepseek-v3:latest",
"size": "404GB",
"context": "160K",
"inputType": "Text"
},
{
"name": "deepseek-v3:671b",
"size": "404GB",
"context": "160K",
"inputType": "Text"
}
]
}
data/models/devstral.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "devstral",
"url": "https://ollama.com/library/devstral",
"description": "Devstral: the best open source model for coding agents",
"variantsCount": 2,
"variants": [
{
"name": "devstral:latest",
"size": "14GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "devstral:24b",
"size": "14GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/dolphin-llama3.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "dolphin-llama3",
"url": "https://ollama.com/library/dolphin-llama3",
"description": "Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills.",
"variantsCount": 3,
"variants": [
{
"name": "dolphin-llama3:latest",
"size": "4.7GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "dolphin-llama3:8b",
"size": "4.7GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "dolphin-llama3:70b",
"size": "40GB",
"context": "8K",
"inputType": "Text"
}
]
}
data/models/dolphin-mistral.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "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.",
"variantsCount": 2,
"variants": [
{
"name": "dolphin-mistral:latest",
"size": "4.1GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "dolphin-mistral:7b",
"size": "4.1GB",
"context": "32K",
"inputType": "Text"
}
]
}
data/models/dolphin-mixtral.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "dolphin-mixtral",
"url": "https://ollama.com/library/dolphin-mixtral",
"description": "Uncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford.",
"variantsCount": 3,
"variants": [
{
"name": "dolphin-mixtral:latest",
"size": "26GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "dolphin-mixtral:8x7b",
"size": "26GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "dolphin-mixtral:8x22b",
"size": "80GB",
"context": "64K",
"inputType": "Text"
}
]
}
data/models/dolphin-phi.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "dolphin-phi",
"url": "https://ollama.com/library/dolphin-phi",
"description": "2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.",
"variantsCount": 2,
"variants": [
{
"name": "dolphin-phi:latest",
"size": "1.6GB",
"context": "2K",
"inputType": "Text"
},
{
"name": "dolphin-phi:2.7b",
"size": "1.6GB",
"context": "2K",
"inputType": "Text"
}
]
}
data/models/dolphin3.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "dolphin3",
"url": "https://ollama.com/library/dolphin3",
"description": "Dolphin 3.0 Llama 3.1 8B 🐬 is the next generation of the Dolphin series of instruct-tuned models designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.",
"variantsCount": 2,
"variants": [
{
"name": "dolphin3:latest",
"size": "4.9GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "dolphin3:8b",
"size": "4.9GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/dolphincoder.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "dolphincoder",
"url": "https://ollama.com/library/dolphincoder",
"description": "A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.",
"variantsCount": 3,
"variants": [
{
"name": "dolphincoder:latest",
"size": "4.2GB",
"context": "16K",
"inputType": "Text"
},
{
"name": "dolphincoder:7b",
"size": "4.2GB",
"context": "16K",
"inputType": "Text"
},
{
"name": "dolphincoder:15b",
"size": "9.1GB",
"context": "16K",
"inputType": "Text"
}
]
}
data/models/duckdb-nsql.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "duckdb-nsql",
"url": "https://ollama.com/library/duckdb-nsql",
"description": "7B parameter text-to-SQL model made by MotherDuck and Numbers Station.",
"variantsCount": 2,
"variants": [
{
"name": "duckdb-nsql:latest",
"size": "3.8GB",
"context": "16K",
"inputType": "Text"
},
{
"name": "duckdb-nsql:7b",
"size": "3.8GB",
"context": "16K",
"inputType": "Text"
}
]
}
data/models/embeddinggemma.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "embeddinggemma",
"url": "https://ollama.com/library/embeddinggemma",
"description": "EmbeddingGemma is a 300M parameter embedding model from Google.",
"variantsCount": 2,
"variants": [
{
"name": "embeddinggemma:latest",
"size": "622MB",
"context": "2K",
"inputType": "Text"
},
{
"name": "embeddinggemma:300m",
"size": "622MB",
"context": "2K",
"inputType": "Text"
}
]
}
data/models/everythinglm.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "everythinglm",
"url": "https://ollama.com/library/everythinglm",
"description": "Uncensored Llama2 based model with support for a 16K context window.",
"variantsCount": 2,
"variants": [
{
"name": "everythinglm:latest",
"size": "7.4GB",
"context": "16K",
"inputType": "Text"
},
{
"name": "everythinglm:13b",
"size": "7.4GB",
"context": "16K",
"inputType": "Text"
}
]
}
data/models/exaone-deep.json
+32
View File
@@ -0,0 +1,32 @@
{
"model": "exaone-deep",
"url": "https://ollama.com/library/exaone-deep",
"description": "EXAONE Deep exhibits superior capabilities in various reasoning tasks including math and coding benchmarks, ranging from 2.4B to 32B parameters developed and released by LG AI Research.",
"variantsCount": 4,
"variants": [
{
"name": "exaone-deep:latest",
"size": "4.8GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "exaone-deep:2.4b",
"size": "1.6GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "exaone-deep:7.8b",
"size": "4.8GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "exaone-deep:32b",
"size": "19GB",
"context": "32K",
"inputType": "Text"
}
]
}
data/models/exaone3.5.json
+32
View File
@@ -0,0 +1,32 @@
{
"model": "exaone3.5",
"url": "https://ollama.com/library/exaone3.5",
"description": "EXAONE 3.5 is a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research. ",
"variantsCount": 4,
"variants": [
{
"name": "exaone3.5:latest",
"size": "4.8GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "exaone3.5:2.4b",
"size": "1.6GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "exaone3.5:7.8b",
"size": "4.8GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "exaone3.5:32b",
"size": "19GB",
"context": "32K",
"inputType": "Text"
}
]
}
data/models/falcon.json
+32
View File
@@ -0,0 +1,32 @@
{
"model": "falcon",
"url": "https://ollama.com/library/falcon",
"description": "A large language model built by the Technology Innovation Institute (TII) for use in summarization, text generation, and chat bots.",
"variantsCount": 4,
"variants": [
{
"name": "falcon:latest",
"size": "4.2GB",
"context": "2K",
"inputType": "Text"
},
{
"name": "falcon:7b",
"size": "4.2GB",
"context": "2K",
"inputType": "Text"
},
{
"name": "falcon:40b",
"size": "24GB",
"context": "2K",
"inputType": "Text"
},
{
"name": "falcon:180b",
"size": "101GB",
"context": "2K",
"inputType": "Text"
}
]
}
data/models/falcon2.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "falcon2",
"url": "https://ollama.com/library/falcon2",
"description": "Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens.",
"variantsCount": 2,
"variants": [
{
"name": "falcon2:latest",
"size": "6.4GB",
"context": "2K",
"inputType": "Text"
},
{
"name": "falcon2:11b",
"size": "6.4GB",
"context": "2K",
"inputType": "Text"
}
]
}
data/models/falcon3.json
+38
View File
@@ -0,0 +1,38 @@
{
"model": "falcon3",
"url": "https://ollama.com/library/falcon3",
"description": "A family of efficient AI models under 10B parameters performant in science, math, and coding through innovative training techniques.",
"variantsCount": 5,
"variants": [
{
"name": "falcon3:latest",
"size": "4.6GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "falcon3:1b",
"size": "1.8GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "falcon3:3b",
"size": "2.0GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "falcon3:7b",
"size": "4.6GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "falcon3:10b",
"size": "6.3GB",
"context": "32K",
"inputType": "Text"
}
]
}
data/models/firefunction-v2.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "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.",
"variantsCount": 2,
"variants": [
{
"name": "firefunction-v2:latest",
"size": "40GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "firefunction-v2:70b",
"size": "40GB",
"context": "8K",
"inputType": "Text"
}
]
}
data/models/gemini-3-pro-preview.json
+14
View File
@@ -0,0 +1,14 @@
{
"model": "gemini-3-pro-preview",
"url": "https://ollama.com/library/gemini-3-pro-preview",
"description": "Google's most intelligent model with SOTA reasoning and multimodal understanding, and powerful agentic and vibe coding capabilities.",
"variantsCount": 1,
"variants": [
{
"name": "gemini-3-pro-preview:latest",
"size": "-",
"context": "1M",
"inputType": "Text"
}
]
}
data/models/gemma.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "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",
"variantsCount": 3,
"variants": [
{
"name": "gemma:latest",
"size": "5.0GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "gemma:2b",
"size": "1.7GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "gemma:7b",
"size": "5.0GB",
"context": "8K",
"inputType": "Text"
}
]
}
data/models/gemma2.json
+32
View File
@@ -0,0 +1,32 @@
{
"model": "gemma2",
"url": "https://ollama.com/library/gemma2",
"description": "Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.",
"variantsCount": 4,
"variants": [
{
"name": "gemma2:latest",
"size": "5.4GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "gemma2:2b",
"size": "1.6GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "gemma2:9b",
"size": "5.4GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "gemma2:27b",
"size": "16GB",
"context": "8K",
"inputType": "Text"
}
]
}
data/models/gemma3.json
+44
View File
@@ -0,0 +1,44 @@
{
"model": "gemma3",
"url": "https://ollama.com/library/gemma3",
"description": "The current, most capable model that runs on a single GPU.",
"variantsCount": 6,
"variants": [
{
"name": "gemma3:latest",
"size": "3.3GB",
"context": "128K",
"inputType": "Text, Image"
},
{
"name": "gemma3:270m",
"size": "292MB",
"context": "32K",
"inputType": "Text"
},
{
"name": "gemma3:1b",
"size": "815MB",
"context": "32K",
"inputType": "Text"
},
{
"name": "gemma3:4b",
"size": "3.3GB",
"context": "128K",
"inputType": "Text, Image"
},
{
"name": "gemma3:12b",
"size": "8.1GB",
"context": "128K",
"inputType": "Text, Image"
},
{
"name": "gemma3:27b",
"size": "17GB",
"context": "128K",
"inputType": "Text, Image"
}
]
}
data/models/gemma3n.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "gemma3n",
"url": "https://ollama.com/library/gemma3n",
"description": "Gemma 3n models are designed for efficient execution on everyday devices such as laptops, tablets or phones. ",
"variantsCount": 3,
"variants": [
{
"name": "gemma3n:latest",
"size": "7.5GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "gemma3n:e2b",
"size": "5.6GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "gemma3n:e4b",
"size": "7.5GB",
"context": "32K",
"inputType": "Text"
}
]
}
data/models/glm-4.6.json
+14
View File
@@ -0,0 +1,14 @@
{
"model": "glm-4.6",
"url": "https://ollama.com/library/glm-4.6",
"description": "Advanced agentic, reasoning and coding capabilities.",
"variantsCount": 1,
"variants": [
{
"name": "glm-4.6:cloud",
"size": "-",
"context": "198K",
"inputType": "Text"
}
]
}
data/models/glm4.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "glm4",
"url": "https://ollama.com/library/glm4",
"description": "A strong multi-lingual general language model with competitive performance to Llama 3.",
"variantsCount": 2,
"variants": [
{
"name": "glm4:latest",
"size": "5.5GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "glm4:9b",
"size": "5.5GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/goliath.json
+104
View File
@@ -0,0 +1,104 @@
{
"model": "goliath",
"url": "https://ollama.com/library/goliath",
"description": "A language model created by combining two fine-tuned Llama 2 70B models into one.",
"variantsCount": 16,
"variants": [
{
"name": "goliath:latest",
"size": "66GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "goliath:120b-q2_K",
"size": "50GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "goliath:120b-q3_K_S",
"size": "51GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "goliath:120b-q3_K_M",
"size": "56GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "goliath:120b-q3_K_L",
"size": "62GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "goliath:120b-q4_0",
"size": "66GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "goliath:120b-q4_1",
"size": "74GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "goliath:120b-q4_K_S",
"size": "66GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "goliath:120b-q4_K_M",
"size": "71GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "goliath:120b-q5_0",
"size": "81GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "goliath:120b-q5_1",
"size": "88GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "goliath:120b-q5_K_S",
"size": "81GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "goliath:120b-q5_K_M",
"size": "83GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "goliath:120b-q6_K",
"size": "97GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "goliath:120b-q8_0",
"size": "125GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "goliath:120b-fp16",
"size": "236GB",
"context": "4K",
"inputType": "Text"
}
]
}
data/models/gpt-oss-safeguard.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "gpt-oss-safeguard",
"url": "https://ollama.com/library/gpt-oss-safeguard",
"description": "gpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss",
"variantsCount": 3,
"variants": [
{
"name": "gpt-oss-safeguard:latest",
"size": "14GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "gpt-oss-safeguard:20b",
"size": "14GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "gpt-oss-safeguard:120b",
"size": "65GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/gpt-oss.json
+38
View File
@@ -0,0 +1,38 @@
{
"model": "gpt-oss",
"url": "https://ollama.com/library/gpt-oss",
"description": "OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.",
"variantsCount": 5,
"variants": [
{
"name": "gpt-oss:latest",
"size": "14GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "gpt-oss:20b",
"size": "14GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "gpt-oss:120b",
"size": "65GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "gpt-oss:20b-cloud",
"size": "-",
"context": "128K",
"inputType": "Text"
},
{
"name": "gpt-oss:120b-cloud",
"size": "-",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/granite-code.json
+38
View File
@@ -0,0 +1,38 @@
{
"model": "granite-code",
"url": "https://ollama.com/library/granite-code",
"description": "A family of open foundation models by IBM for Code Intelligence",
"variantsCount": 5,
"variants": [
{
"name": "granite-code:latest",
"size": "2.0GB",
"context": "125K",
"inputType": "Text"
},
{
"name": "granite-code:3b",
"size": "2.0GB",
"context": "125K",
"inputType": "Text"
},
{
"name": "granite-code:8b",
"size": "4.6GB",
"context": "125K",
"inputType": "Text"
},
{
"name": "granite-code:20b",
"size": "12GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "granite-code:34b",
"size": "19GB",
"context": "8K",
"inputType": "Text"
}
]
}
data/models/granite-embedding.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "granite-embedding",
"url": "https://ollama.com/library/granite-embedding",
"description": "The IBM Granite Embedding 30M and 278M models models are text-only dense biencoder embedding models, with 30M available in English only and 278M serving multilingual use cases.",
"variantsCount": 3,
"variants": [
{
"name": "granite-embedding:latest",
"size": "63MB",
"context": "512",
"inputType": "Text"
},
{
"name": "granite-embedding:30m",
"size": "63MB",
"context": "512",
"inputType": "Text"
},
{
"name": "granite-embedding:278m",
"size": "563MB",
"context": "512",
"inputType": "Text"
}
]
}
data/models/granite3-dense.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "granite3-dense",
"url": "https://ollama.com/library/granite3-dense",
"description": "The IBM Granite 2B and 8B models are designed to support tool-based use cases and support for retrieval augmented generation (RAG), streamlining code generation, translation and bug fixing.",
"variantsCount": 3,
"variants": [
{
"name": "granite3-dense:latest",
"size": "1.6GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "granite3-dense:2b",
"size": "1.6GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "granite3-dense:8b",
"size": "4.9GB",
"context": "4K",
"inputType": "Text"
}
]
}
data/models/granite3-guardian.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "granite3-guardian",
"url": "https://ollama.com/library/granite3-guardian",
"description": "The IBM Granite Guardian 3.0 2B and 8B models are designed to detect risks in prompts and/or responses.",
"variantsCount": 3,
"variants": [
{
"name": "granite3-guardian:latest",
"size": "2.7GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "granite3-guardian:2b",
"size": "2.7GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "granite3-guardian:8b",
"size": "5.8GB",
"context": "8K",
"inputType": "Text"
}
]
}
data/models/granite3-moe.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "granite3-moe",
"url": "https://ollama.com/library/granite3-moe",
"description": "The IBM Granite 1B and 3B models are the first mixture of experts (MoE) Granite models from IBM designed for low latency usage.",
"variantsCount": 3,
"variants": [
{
"name": "granite3-moe:latest",
"size": "822MB",
"context": "4K",
"inputType": "Text"
},
{
"name": "granite3-moe:1b",
"size": "822MB",
"context": "4K",
"inputType": "Text"
},
{
"name": "granite3-moe:3b",
"size": "2.1GB",
"context": "4K",
"inputType": "Text"
}
]
}
data/models/granite3.1-dense.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "granite3.1-dense",
"url": "https://ollama.com/library/granite3.1-dense",
"description": "The IBM Granite 2B and 8B models are text-only dense LLMs trained on over 12 trillion tokens of data, demonstrated significant improvements over their predecessors in performance and speed in IBM’s initial testing.",
"variantsCount": 3,
"variants": [
{
"name": "granite3.1-dense:latest",
"size": "5.0GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "granite3.1-dense:2b",
"size": "1.6GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "granite3.1-dense:8b",
"size": "5.0GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/granite3.1-moe.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "granite3.1-moe",
"url": "https://ollama.com/library/granite3.1-moe",
"description": "The IBM Granite 1B and 3B models are long-context mixture of experts (MoE) Granite models from IBM designed for low latency usage.",
"variantsCount": 3,
"variants": [
{
"name": "granite3.1-moe:latest",
"size": "2.0GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "granite3.1-moe:1b",
"size": "1.4GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "granite3.1-moe:3b",
"size": "2.0GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/granite3.2-vision.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "granite3.2-vision",
"url": "https://ollama.com/library/granite3.2-vision",
"description": "A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.",
"variantsCount": 2,
"variants": [
{
"name": "granite3.2-vision:latest",
"size": "2.4GB",
"context": "16K",
"inputType": "Text, Image"
},
{
"name": "granite3.2-vision:2b",
"size": "2.4GB",
"context": "16K",
"inputType": "Text, Image"
}
]
}
data/models/granite3.2.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "granite3.2",
"url": "https://ollama.com/library/granite3.2",
"description": "Granite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.",
"variantsCount": 3,
"variants": [
{
"name": "granite3.2:latest",
"size": "4.9GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "granite3.2:2b",
"size": "1.5GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "granite3.2:8b",
"size": "4.9GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/granite3.3.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "granite3.3",
"url": "https://ollama.com/library/granite3.3",
"description": "IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.",
"variantsCount": 3,
"variants": [
{
"name": "granite3.3:latest",
"size": "4.9GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "granite3.3:2b",
"size": "1.5GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "granite3.3:8b",
"size": "4.9GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/granite4.json
+32
View File
@@ -0,0 +1,32 @@
{
"model": "granite4",
"url": "https://ollama.com/library/granite4",
"description": "Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.",
"variantsCount": 4,
"variants": [
{
"name": "granite4:latest",
"size": "2.1GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "granite4:350m",
"size": "708MB",
"context": "32K",
"inputType": "Text"
},
{
"name": "granite4:1b",
"size": "3.3GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "granite4:3b",
"size": "2.1GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/hermes3.json
+38
View File
@@ -0,0 +1,38 @@
{
"model": "hermes3",
"url": "https://ollama.com/library/hermes3",
"description": "Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research",
"variantsCount": 5,
"variants": [
{
"name": "hermes3:latest",
"size": "4.7GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "hermes3:3b",
"size": "2.0GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "hermes3:8b",
"size": "4.7GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "hermes3:70b",
"size": "40GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "hermes3:405b",
"size": "229GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/internlm2.json
+38
View File
@@ -0,0 +1,38 @@
{
"model": "internlm2",
"url": "https://ollama.com/library/internlm2",
"description": "InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability.",
"variantsCount": 5,
"variants": [
{
"name": "internlm2:latest",
"size": "4.5GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "internlm2:1m",
"size": "4.5GB",
"context": "256K",
"inputType": "Text"
},
{
"name": "internlm2:1.8b",
"size": "1.1GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "internlm2:7b",
"size": "4.5GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "internlm2:20b",
"size": "11GB",
"context": "32K",
"inputType": "Text"
}
]
}
data/models/kimi-k2-thinking.json
+14
View File
@@ -0,0 +1,14 @@
{
"model": "kimi-k2-thinking",
"url": "https://ollama.com/library/kimi-k2-thinking",
"description": "Kimi K2 Thinking, Moonshot AI's best open-source thinking model.",
"variantsCount": 1,
"variants": [
{
"name": "kimi-k2-thinking:cloud",
"size": "-",
"context": "256K",
"inputType": "Text"
}
]
}
data/models/kimi-k2.json
+14
View File
@@ -0,0 +1,14 @@
{
"model": "kimi-k2",
"url": "https://ollama.com/library/kimi-k2",
"description": "A state-of-the-art mixture-of-experts (MoE) language model. Kimi K2-Instruct-0905 demonstrates significant improvements in performance on public benchmarks and real-world coding agent tasks.",
"variantsCount": 1,
"variants": [
{
"name": "kimi-k2:1t-cloud",
"size": "-",
"context": "256K",
"inputType": "Text"
}
]
}
data/models/llama-guard3.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "llama-guard3",
"url": "https://ollama.com/library/llama-guard3",
"description": "Llama Guard 3 is a series of models fine-tuned for content safety classification of LLM inputs and responses.",
"variantsCount": 3,
"variants": [
{
"name": "llama-guard3:latest",
"size": "4.9GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "llama-guard3:1b",
"size": "1.6GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "llama-guard3:8b",
"size": "4.9GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/llama-pro.json
+206
View File
@@ -0,0 +1,206 @@
{
"model": "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.",
"variantsCount": 33,
"variants": [
{
"name": "llama-pro:latest",
"size": "4.7GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:instruct",
"size": "4.7GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:text",
"size": "4.7GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-instruct-q2_K",
"size": "3.5GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-instruct-q3_K_S",
"size": "3.6GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-instruct-q3_K_M",
"size": "4.1GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-instruct-q3_K_L",
"size": "4.5GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-instruct-q4_0",
"size": "4.7GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-instruct-q4_1",
"size": "5.3GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-instruct-q4_K_S",
"size": "4.8GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-instruct-q4_K_M",
"size": "5.1GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-instruct-q5_0",
"size": "5.8GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-instruct-q5_1",
"size": "6.3GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-instruct-q5_K_S",
"size": "5.8GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-instruct-q5_K_M",
"size": "5.9GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-instruct-q6_K",
"size": "6.9GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-instruct-q8_0",
"size": "8.9GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-instruct-fp16",
"size": "17GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-text-q2_K",
"size": "3.5GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-text-q3_K_S",
"size": "3.6GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-text-q3_K_M",
"size": "4.1GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-text-q3_K_L",
"size": "4.5GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-text-q4_0",
"size": "4.7GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-text-q4_1",
"size": "5.3GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-text-q4_K_S",
"size": "4.8GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-text-q4_K_M",
"size": "5.1GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-text-q5_0",
"size": "5.8GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-text-q5_1",
"size": "6.3GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-text-q5_K_S",
"size": "5.8GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-text-q5_K_M",
"size": "5.9GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-text-q6_K",
"size": "6.9GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-text-q8_0",
"size": "8.9GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama-pro:8b-text-fp16",
"size": "17GB",
"context": "4K",
"inputType": "Text"
}
]
}
data/models/llama2-chinese.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "llama2-chinese",
"url": "https://ollama.com/library/llama2-chinese",
"description": "Llama 2 based model fine tuned to improve Chinese dialogue ability.",
"variantsCount": 3,
"variants": [
{
"name": "llama2-chinese:latest",
"size": "3.8GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama2-chinese:7b",
"size": "3.8GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama2-chinese:13b",
"size": "7.4GB",
"context": "4K",
"inputType": "Text"
}
]
}
data/models/llama2-uncensored.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "llama2-uncensored",
"url": "https://ollama.com/library/llama2-uncensored",
"description": "Uncensored Llama 2 model by George Sung and Jarrad Hope.",
"variantsCount": 3,
"variants": [
{
"name": "llama2-uncensored:latest",
"size": "3.8GB",
"context": "2K",
"inputType": "Text"
},
{
"name": "llama2-uncensored:7b",
"size": "3.8GB",
"context": "2K",
"inputType": "Text"
},
{
"name": "llama2-uncensored:70b",
"size": "39GB",
"context": "2K",
"inputType": "Text"
}
]
}
data/models/llama2.json
+32
View File
@@ -0,0 +1,32 @@
{
"model": "llama2",
"url": "https://ollama.com/library/llama2",
"description": "Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters.",
"variantsCount": 4,
"variants": [
{
"name": "llama2:latest",
"size": "3.8GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama2:7b",
"size": "3.8GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama2:13b",
"size": "7.4GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llama2:70b",
"size": "39GB",
"context": "4K",
"inputType": "Text"
}
]
}
data/models/llama3-chatqa.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "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).",
"variantsCount": 3,
"variants": [
{
"name": "llama3-chatqa:latest",
"size": "4.7GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "llama3-chatqa:8b",
"size": "4.7GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "llama3-chatqa:70b",
"size": "40GB",
"context": "8K",
"inputType": "Text"
}
]
}
data/models/llama3-gradient.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "llama3-gradient",
"url": "https://ollama.com/library/llama3-gradient",
"description": "This model extends LLama-3 8B's context length from 8k to over 1m tokens.",
"variantsCount": 3,
"variants": [
{
"name": "llama3-gradient:latest",
"size": "4.7GB",
"context": "1M",
"inputType": "Text"
},
{
"name": "llama3-gradient:8b",
"size": "4.7GB",
"context": "1M",
"inputType": "Text"
},
{
"name": "llama3-gradient:70b",
"size": "40GB",
"context": "1M",
"inputType": "Text"
}
]
}
data/models/llama3-groq-tool-use.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "llama3-groq-tool-use",
"url": "https://ollama.com/library/llama3-groq-tool-use",
"description": "A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.",
"variantsCount": 3,
"variants": [
{
"name": "llama3-groq-tool-use:latest",
"size": "4.7GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "llama3-groq-tool-use:8b",
"size": "4.7GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "llama3-groq-tool-use:70b",
"size": "40GB",
"context": "8K",
"inputType": "Text"
}
]
}
data/models/llama3.1.json
+32
View File
@@ -0,0 +1,32 @@
{
"model": "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.",
"variantsCount": 4,
"variants": [
{
"name": "llama3.1:latest",
"size": "4.9GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "llama3.1:8b",
"size": "4.9GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "llama3.1:70b",
"size": "43GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "llama3.1:405b",
"size": "243GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/llama3.2-vision.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "llama3.2-vision",
"url": "https://ollama.com/library/llama3.2-vision",
"description": "Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.",
"variantsCount": 3,
"variants": [
{
"name": "llama3.2-vision:latest",
"size": "7.8GB",
"context": "128K",
"inputType": "Text, Image"
},
{
"name": "llama3.2-vision:11b",
"size": "7.8GB",
"context": "128K",
"inputType": "Text, Image"
},
{
"name": "llama3.2-vision:90b",
"size": "55GB",
"context": "128K",
"inputType": "Text, Image"
}
]
}
data/models/llama3.2.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "llama3.2",
"url": "https://ollama.com/library/llama3.2",
"description": "Meta's Llama 3.2 goes small with 1B and 3B models. ",
"variantsCount": 3,
"variants": [
{
"name": "llama3.2:latest",
"size": "2.0GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "llama3.2:1b",
"size": "1.3GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "llama3.2:3b",
"size": "2.0GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/llama3.3.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "llama3.3",
"url": "https://ollama.com/library/llama3.3",
"description": "New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.",
"variantsCount": 2,
"variants": [
{
"name": "llama3.3:latest",
"size": "43GB",
"context": "128K",
"inputType": "Text"
},
{
"name": "llama3.3:70b",
"size": "43GB",
"context": "128K",
"inputType": "Text"
}
]
}
data/models/llama3.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "llama3",
"url": "https://ollama.com/library/llama3",
"description": "Meta Llama 3: The most capable openly available LLM to date",
"variantsCount": 3,
"variants": [
{
"name": "llama3:latest",
"size": "4.7GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "llama3:8b",
"size": "4.7GB",
"context": "8K",
"inputType": "Text"
},
{
"name": "llama3:70b",
"size": "40GB",
"context": "8K",
"inputType": "Text"
}
]
}
data/models/llama4.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "llama4",
"url": "https://ollama.com/library/llama4",
"description": "Meta's latest collection of multimodal models.",
"variantsCount": 3,
"variants": [
{
"name": "llama4:latest",
"size": "67GB",
"context": "10M",
"inputType": "Text, Image"
},
{
"name": "llama4:16x17b",
"size": "67GB",
"context": "10M",
"inputType": "Text, Image"
},
{
"name": "llama4:128x17b",
"size": "245GB",
"context": "1M",
"inputType": "Text, Image"
}
]
}
data/models/llava-llama3.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "llava-llama3",
"url": "https://ollama.com/library/llava-llama3",
"description": "A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.",
"variantsCount": 2,
"variants": [
{
"name": "llava-llama3:latest",
"size": "5.5GB",
"context": "8K",
"inputType": "Text, Image"
},
{
"name": "llava-llama3:8b",
"size": "5.5GB",
"context": "8K",
"inputType": "Text, Image"
}
]
}
data/models/llava-phi3.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "llava-phi3",
"url": "https://ollama.com/library/llava-phi3",
"description": "A new small LLaVA model fine-tuned from Phi 3 Mini.",
"variantsCount": 2,
"variants": [
{
"name": "llava-phi3:latest",
"size": "2.9GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "llava-phi3:3.8b",
"size": "2.9GB",
"context": "4K",
"inputType": "Text"
}
]
}
data/models/llava.json
+32
View File
@@ -0,0 +1,32 @@
{
"model": "llava",
"url": "https://ollama.com/library/llava",
"description": "🌋 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.",
"variantsCount": 4,
"variants": [
{
"name": "llava:latest",
"size": "4.7GB",
"context": "32K",
"inputType": "Text, Image"
},
{
"name": "llava:7b",
"size": "4.7GB",
"context": "32K",
"inputType": "Text, Image"
},
{
"name": "llava:13b",
"size": "8.0GB",
"context": "4K",
"inputType": "Text, Image"
},
{
"name": "llava:34b",
"size": "20GB",
"context": "4K",
"inputType": "Text"
}
]
}
data/models/magicoder.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "magicoder",
"url": "https://ollama.com/library/magicoder",
"description": "🎩 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.",
"variantsCount": 2,
"variants": [
{
"name": "magicoder:latest",
"size": "3.8GB",
"context": "16K",
"inputType": "Text"
},
{
"name": "magicoder:7b",
"size": "3.8GB",
"context": "16K",
"inputType": "Text"
}
]
}
data/models/magistral.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "magistral",
"url": "https://ollama.com/library/magistral",
"description": "Magistral is a small, efficient reasoning model with 24B parameters.",
"variantsCount": 2,
"variants": [
{
"name": "magistral:latest",
"size": "14GB",
"context": "39K",
"inputType": "Text"
},
{
"name": "magistral:24b",
"size": "14GB",
"context": "39K",
"inputType": "Text"
}
]
}
data/models/marco-o1.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "marco-o1",
"url": "https://ollama.com/library/marco-o1",
"description": "An open large reasoning model for real-world solutions by the Alibaba International Digital Commerce Group (AIDC-AI).",
"variantsCount": 2,
"variants": [
{
"name": "marco-o1:latest",
"size": "4.7GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "marco-o1:7b",
"size": "4.7GB",
"context": "32K",
"inputType": "Text"
}
]
}
data/models/mathstral.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "mathstral",
"url": "https://ollama.com/library/mathstral",
"description": "MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI.",
"variantsCount": 2,
"variants": [
{
"name": "mathstral:latest",
"size": "4.1GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "mathstral:7b",
"size": "4.1GB",
"context": "32K",
"inputType": "Text"
}
]
}
data/models/meditron.json
+26
View File
@@ -0,0 +1,26 @@
{
"model": "meditron",
"url": "https://ollama.com/library/meditron",
"description": "Open-source medical large language model adapted from Llama 2 to the medical domain.",
"variantsCount": 3,
"variants": [
{
"name": "meditron:latest",
"size": "3.8GB",
"context": "2K",
"inputType": "Text"
},
{
"name": "meditron:7b",
"size": "3.8GB",
"context": "2K",
"inputType": "Text"
},
{
"name": "meditron:70b",
"size": "39GB",
"context": "4K",
"inputType": "Text"
}
]
}
data/models/medllama2.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "medllama2",
"url": "https://ollama.com/library/medllama2",
"description": "Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset. ",
"variantsCount": 2,
"variants": [
{
"name": "medllama2:latest",
"size": "3.8GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "medllama2:7b",
"size": "3.8GB",
"context": "4K",
"inputType": "Text"
}
]
}
data/models/megadolphin.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "megadolphin",
"url": "https://ollama.com/library/megadolphin",
"description": "MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself.",
"variantsCount": 2,
"variants": [
{
"name": "megadolphin:latest",
"size": "68GB",
"context": "4K",
"inputType": "Text"
},
{
"name": "megadolphin:120b",
"size": "68GB",
"context": "4K",
"inputType": "Text"
}
]
}
data/models/minicpm-v.json
+20
View File
@@ -0,0 +1,20 @@
{
"model": "minicpm-v",
"url": "https://ollama.com/library/minicpm-v",
"description": "A series of multimodal LLMs (MLLMs) designed for vision-language understanding.",
"variantsCount": 2,
"variants": [
{
"name": "minicpm-v:latest",
"size": "5.5GB",
"context": "32K",
"inputType": "Text"
},
{
"name": "minicpm-v:8b",
"size": "5.5GB",
"context": "32K",
"inputType": "Text"
}
]
}
data/models/minimax-m2.json
+14
View File
@@ -0,0 +1,14 @@
{
"model": "minimax-m2",
"url": "https://ollama.com/library/minimax-m2",
"description": "MiniMax M2 is a high-efficiency large language model built for coding and agentic workflows.",
"variantsCount": 1,
"variants": [
{
"name": "minimax-m2:cloud",
"size": "-",
"context": "200K",
"inputType": "Text"
}
]
}
Loaded 100 of 261 files, more files were not shown because too many files have changed in this diff. Show more