Tools models · Ollama Search

qwen3-vl

The most powerful vision-language model in the Qwen model family to date.

vision tools cloud 2b 4b 8b 30b 32b 235b

735.7K Pulls 59 Tags Updated 1 month ago

devstral-2

123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.

tools cloud 123b

3,404 Pulls 6 Tags Updated 2 days ago

gpt-oss

OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.

tools thinking cloud 20b 120b

5.2M Pulls 5 Tags Updated 2 months ago

ministral-3

The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.

vision tools cloud 3b 8b 14b

91.5K Pulls 16 Tags Updated yesterday

deepseek-r1

DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.

tools thinking 1.5b 7b 8b 14b 32b 70b 671b

74.2M Pulls 35 Tags Updated 5 months ago

qwen3-coder

Alibaba's performant long context models for agentic and coding tasks.

tools cloud 30b 480b

1.2M Pulls 10 Tags Updated 2 months ago

devstral-small-2

24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.

vision tools cloud 24b

29K Pulls 6 Tags Updated yesterday

qwen3

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

tools thinking 0.6b 1.7b 4b 8b 14b 30b 32b 235b

15M Pulls 58 Tags Updated 2 months ago

deepseek-v3.1

DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.

tools thinking cloud 671b

199.4K Pulls 8 Tags Updated 2 months ago

llama3.1

Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.

tools 8b 70b 405b

107.5M Pulls 93 Tags Updated 1 year ago

llama3.2

Meta's Llama 3.2 goes small with 1B and 3B models.

tools 1b 3b

49.5M Pulls 63 Tags Updated 1 year ago

mistral

The 7B model released by Mistral AI, updated to version 0.3.

tools 7b

23.1M Pulls 84 Tags Updated 5 months ago

qwen2.5

Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.

tools 0.5b 1.5b 3b 7b 14b 32b 72b

18M Pulls 133 Tags Updated 1 year ago

qwen2.5-coder

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.

tools 0.5b 1.5b 3b 7b 14b 32b

9.2M Pulls 199 Tags Updated 6 months ago

qwen2

Qwen2 is a new series of large language models from Alibaba group

tools 0.5b 1.5b 7b 72b

4.5M Pulls 97 Tags Updated 1 year ago

mistral-nemo

A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.

tools 12b

3M Pulls 17 Tags Updated 4 months ago

llama3.3

New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.

tools 70b

2.8M Pulls 14 Tags Updated 1 year ago

smollm2

SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.

tools 135m 360m 1.7b

2.2M Pulls 49 Tags Updated 1 year ago

mistral-small

Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.

tools 22b 24b

2.2M Pulls 21 Tags Updated 10 months ago

qwq

QwQ is the reasoning model of the Qwen series.

tools 32b

1.9M Pulls 8 Tags Updated 9 months ago

mixtral

A set of Mixture of Experts (MoE) model with open weights by Mistral AI in 8x7b and 8x22b parameter sizes.

tools 8x7b 8x22b

1.5M Pulls 70 Tags Updated 11 months ago

granite3.1-moe

The IBM Granite 1B and 3B models are long-context mixture of experts (MoE) Granite models from IBM designed for low latency usage.

tools 1b 3b

1.5M Pulls 33 Tags Updated 11 months ago

cogito

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.

tools 3b 8b 14b 32b 70b

916.9K Pulls 20 Tags Updated 8 months ago

llama4

Meta's latest collection of multimodal models.

vision tools 16x17b 128x17b

885.4K Pulls 11 Tags Updated 6 months ago

mistral-small3.2

An update to Mistral Small that improves on function calling, instruction following, and less repetition errors.

vision tools 24b

879.5K Pulls 5 Tags Updated 5 months ago

magistral

Magistral is a small, efficient reasoning model with 24B parameters.

tools thinking 24b

809.6K Pulls 5 Tags Updated 6 months ago

granite3.3

IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.

tools 2b 8b

763.2K Pulls 3 Tags Updated 8 months ago

phi4-mini

Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.

tools 3.8b

633.9K Pulls 5 Tags Updated 9 months ago

granite3.2-vision

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.

vision tools 2b

546.5K Pulls 5 Tags Updated 9 months ago

devstral

Devstral: the best open source model for coding agents

tools 24b

534.1K Pulls 5 Tags Updated 5 months ago

mistral-small3.1

Building upon Mistral Small 3, Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance.

vision tools 24b

436.1K Pulls 5 Tags Updated 8 months ago

command-r

Command R is a Large Language Model optimized for conversational interaction and long context tasks.

tools 35b

420.8K Pulls 32 Tags Updated 1 year ago

hermes3

Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research

tools 3b 8b 70b 405b

367K Pulls 65 Tags Updated 12 months ago

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.

tools 123b

295.2K Pulls 32 Tags Updated 1 year ago

granite4

Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.

tools 350m 1b 3b

285.8K Pulls 17 Tags Updated 1 month ago

command-r-plus

Command R+ is a powerful, scalable large language model purpose-built to excel at real-world enterprise use cases.

tools 104b

200.2K Pulls 21 Tags Updated 1 year ago

granite3.2

Granite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.

tools 2b 8b

185.5K Pulls 9 Tags Updated 9 months ago

granite3-dense

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.

tools 2b 8b

148.5K Pulls 33 Tags Updated 1 year ago

granite3.1-dense

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.

tools 2b 8b

147.5K Pulls 33 Tags Updated 11 months ago

nemotron-mini

A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.

tools 4b

130.1K Pulls 17 Tags Updated 1 year ago

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.

tools 8b 70b

122.5K Pulls 33 Tags Updated 1 year ago

athene-v2

Athene-V2 is a 72B parameter model which excels at code completion, mathematics, and log extraction tasks.

tools 72b

122.2K Pulls 17 Tags Updated 1 year ago

nemotron

Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.

tools 70b

117K Pulls 17 Tags Updated 1 year ago

aya-expanse

Cohere For AI's language models trained to perform well across 23 different languages.

tools 8b 32b

112.2K Pulls 33 Tags Updated 1 year ago

granite3-moe

The IBM Granite 1B and 3B models are the first mixture of experts (MoE) Granite models from IBM designed for low latency usage.

tools 1b 3b

111.3K Pulls 33 Tags Updated 1 year ago

command-r7b

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.

tools 7b

96.5K Pulls 5 Tags Updated 11 months ago

command-a

111 billion parameter model optimized for demanding enterprises that require fast, secure, and high-quality AI

tools 111b

80.6K Pulls 5 Tags Updated 9 months ago

firefunction-v2

An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.

tools 70b

56.8K Pulls 17 Tags Updated 1 year ago

command-r7b-arabic

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.

tools 7b

39.6K Pulls 5 Tags Updated 9 months ago

gpt-oss-safeguard

gpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss

tools thinking 20b 120b

29.2K Pulls 3 Tags Updated 1 month ago

qwen3-next

The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.

tools thinking cloud 80b

9,193 Pulls 10 Tags Updated 5 days ago

rnj-1

Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.

tools cloud 8b

5,576 Pulls 6 Tags Updated yesterday