Ollama
Models GitHub Discord Docs Pricing
Sign in Download
Models Download GitHub Discord Docs Pricing Sign in
⇅
Ollama
Search for models on Ollama.
  • functiongemma

    FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.

    tools 270m

    50.2K  Pulls 4  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

    58.8K  Pulls 6  Tags Updated  1 month ago

  • gemini-3-flash-preview

    Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost.

    cloud

    45.9K  Pulls 2  Tags Updated  1 month ago

  • cogito-2.1

    The Cogito v2.1 LLMs are instruction tuned generative models. All models are released under MIT license for commercial use.

    cloud 671b

    53.1K  Pulls 6  Tags Updated  2 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

    54.6K  Pulls 3  Tags Updated  3 months ago

  • glm-4.7

    Advancing the Coding Capability

    cloud

    20.8K  Pulls 1  Tag Updated  1 month ago

  • nomic-embed-text-v2-moe

    nomic-embed-text-v2-moe is a multilingual MoE text embedding model that excels at multilingual retrieval.

    embedding

    24.8K  Pulls 1  Tag Updated  1 month ago

  • glm-4.6

    Advanced agentic, reasoning and coding capabilities.

    cloud

    52.3K  Pulls 1  Tag Updated  3 months ago

  • minimax-m2

    MiniMax M2 is a high-efficiency large language model built for coding and agentic workflows.

    cloud

    44K  Pulls 1  Tag Updated  3 months ago

  • deepseek-v3.2

    DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance.

    cloud

    18K  Pulls 1  Tag Updated  1 month ago

  • minimax-m2.1

    Exceptional multilingual capabilities to elevate code engineering

    cloud

    11.4K  Pulls 1  Tag Updated  1 month ago

  • kimi-k2-thinking

    Kimi K2 Thinking, Moonshot AI's best open-source thinking model.

    cloud

    24.2K  Pulls 1  Tag Updated  2 months ago

  • kimi-k2

    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.

    cloud

    33.1K  Pulls 1  Tag Updated  4 months ago

  • mistral-large-3

    A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.

    cloud

    13.3K  Pulls 1  Tag Updated  1 month ago

  • gemma3

    The current, most capable model that runs on a single GPU.

    vision cloud 270m 1b 4b 12b 27b

    30.8M  Pulls 29  Tags Updated  1 month ago

  • 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

    18.1M  Pulls 58  Tags Updated  3 months ago

  • mistral-small3.2

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

    vision tools 24b

    1.2M  Pulls 5  Tags Updated  7 months ago

  • gemma3n

    Gemma 3n models are designed for efficient execution on everyday devices such as laptops, tablets or phones.

    e2b e4b

    1.1M  Pulls 9  Tags Updated  7 months ago

  • qwen2.5vl

    Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.

    vision 3b 7b 32b 72b

    1.2M  Pulls 17  Tags Updated  8 months ago

  • magistral

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

    tools thinking 24b

    1M  Pulls 5  Tags Updated  7 months ago

© 2026 Ollama
Blog Contact