Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
  • lfm2

    LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient.

    tools 24b

    919.3K  Pulls 6  Tags Updated  1 week ago

  • qwen3.5

    Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.

    vision tools thinking cloud 0.8b 2b 4b 9b 27b 35b 122b

    677K  Pulls 30  Tags Updated  3 days ago

  • minimax-m2.5

    MiniMax-M2.5 is a state-of-the-art large language model designed for real-world productivity and coding tasks.

    cloud

    88.4K  Pulls 1  Tag Updated  3 weeks ago

  • glm-5

    A strong reasoning and agentic model from Z.ai with 744B total parameters (40B active), built for complex systems engineering and long-horizon tasks.

    cloud

    81.7K  Pulls 1  Tag Updated  3 weeks ago

  • qwen3-coder-next

    Qwen3-Coder-Next is a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development.

    tools cloud

    735.5K  Pulls 4  Tags Updated  4 weeks ago

  • lfm2.5-thinking

    LFM2.5 is a new family of hybrid models designed for on-device deployment.

    tools 1.2b

    940.4K  Pulls 5  Tags Updated  1 month ago

  • translategemma

    A new collection of open translation models built on Gemma 3, helping people communicate across 55 languages.

    vision 4b 12b 27b

    506.9K  Pulls 13  Tags Updated  1 month ago

  • qwen3-vl

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

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

    1.8M  Pulls 59  Tags Updated  4 months ago

  • glm-4.7-flash

    As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.

    tools thinking

    376.6K  Pulls 4  Tags Updated  1 month ago

  • qwen3-embedding

    Building upon the foundational models of the Qwen3 series, Qwen3 Embedding provides a comprehensive range of text embeddings models in various sizes

    embedding 0.6b 4b 8b

    1.1M  Pulls 12  Tags Updated  5 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

    536.2K  Pulls 16  Tags Updated  2 months ago

  • granite4

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

    tools 350m 1b 3b

    768.7K  Pulls 17  Tags Updated  4 months 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

    358.1K  Pulls 10  Tags Updated  2 months 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

    336.4K  Pulls 6  Tags Updated  2 months ago

  • kimi-k2.5

    Kimi K2.5 is an open-source, native multimodal agentic model that seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.

    cloud

    121.5K  Pulls 1  Tag Updated  1 month ago

  • deepseek-ocr

    DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.

    vision 3b

    320.9K  Pulls 3  Tags Updated  3 months ago

  • nemotron-3-nano

    Nemotron 3 Nano - A new Standard for Efficient, Open, and Intelligent Agentic Models

    tools thinking cloud 30b

    194.3K  Pulls 6  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

    211K  Pulls 6  Tags Updated  2 months ago

  • olmo-3

    Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.

    7b 32b

    182.6K  Pulls 15  Tags Updated  2 months ago

  • glm-ocr

    GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.

    vision tools

    61.8K  Pulls 3  Tags Updated  1 month ago

  • olmo-3.1

    Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.

    tools 32b

    111.4K  Pulls 10  Tags Updated  2 months ago

  • devstral-2

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

    tools cloud 123b

    100K  Pulls 6  Tags Updated  2 months ago

  • functiongemma

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

    tools 270m

    79.6K  Pulls 4  Tags Updated  2 months ago

  • gemini-3-flash-preview

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

    cloud

    73.1K  Pulls 2  Tags Updated  2 months ago

  • glm-4.7

    Advancing the Coding Capability

    cloud

    59.3K  Pulls 1  Tag Updated  2 months 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

    82.1K  Pulls 6  Tags Updated  3 months ago

  • nomic-embed-text-v2-moe

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

    embedding

    51.8K  Pulls 1  Tag 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

    79.4K  Pulls 3  Tags Updated  4 months ago

  • minimax-m2

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

    cloud

    71.1K  Pulls 1  Tag Updated  4 months ago

  • glm-4.6

    Advanced agentic, reasoning and coding capabilities.

    cloud

    77.8K  Pulls 1  Tag Updated  4 months ago

  • deepseek-v3.2

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

    cloud

    41K  Pulls 1  Tag Updated  2 months ago

  • minimax-m2.1

    Exceptional multilingual capabilities to elevate code engineering

    cloud

    21.7K  Pulls 1  Tag Updated  2 months ago

  • kimi-k2-thinking

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

    cloud

    34.3K  Pulls 1  Tag Updated  3 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

    42.4K  Pulls 1  Tag Updated  5 months ago

  • mistral-large-3

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

    cloud

    22.4K  Pulls 1  Tag Updated  3 months ago

  • gemma3

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

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

    32.7M  Pulls 29  Tags Updated  3 months 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

    22.8M  Pulls 58  Tags Updated  4 months ago

  • gpt-oss

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

    tools thinking cloud 20b 120b

    7.4M  Pulls 5  Tags Updated  4 months ago

  • qwen3-coder

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

    tools cloud 30b 480b

    3.4M  Pulls 10  Tags Updated  5 months ago

  • mistral-small3.2

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

    vision tools 24b

    1.3M  Pulls 5  Tags Updated  8 months ago

© 2026 Ollama
Blog Contact