Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
Vison · Ollama
Search for models on Ollama.
  • llama3.2-vision

    Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.

    vision 11b 90b

    5.2M  Pulls 9  Tags Updated  1 year ago

  • qwen3-vl

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

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

    5.8M  Pulls 57  Tags Updated  10 months ago

  • deepseek-ocr

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

    vision 3b

    527.5K  Pulls 3  Tags Updated  9 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

    4.8M  Pulls 17  Tags Updated  1 year ago

  • 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.

    vision 7b 13b 34b

    14.8M  Pulls 98  Tags Updated  2 years ago

  • minicpm-v

    A series of multimodal LLMs (MLLMs) designed for vision-language understanding.

    vision 8b

    5.4M  Pulls 17  Tags Updated  1 year 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

    993.4K  Pulls 5  Tags Updated  1 year ago

  • moondream

    moondream2 is a small vision language model designed to run efficiently on edge devices.

    vision 1.8b

    1.8M  Pulls 18  Tags Updated  2 years 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

    785.7K  Pulls 5  Tags Updated  1 year ago

  • nemotron-3-ultra

    NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.

    tools thinking cloud

    81.3K  Pulls 1  Tag Updated  3 months ago

  • nemotron-cascade-2

    An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.

    tools thinking 30b

    145.8K  Pulls 3  Tags Updated  5 months ago

  • vitali87/shell-commands-qwen2-1.5b

    fine-tuned model on Linux Command Library (https://linuxcommandlibrary.com/basic/oneliners)

    401  Pulls 1  Tag Updated  1 year ago

  • VisionVTAI/Aria-sama

    tools

    29  Pulls 1  Tag Updated  1 year ago

  • deepseek-v4-pro

    DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.

    tools thinking cloud

    385.1K  Pulls 2  Tags Updated  3 weeks ago

  • dcostenco/prism-coder

    Local-first AI tool router. 2B/4B/9B read images (vision); 27B text-only. 14B/32B retired. 99.1-100% routing accuracy (BFCL). 97% of traffic stays local.

    vision tools thinking 2b 4b 9b 14b 27b 32b

    1,896  Pulls 6  Tags Updated  3 weeks ago

  • vickiovikthompson/uncensored-qwen

    Uncensored version of qwen 2.5

    tools

    297  Pulls 1  Tag Updated  5 months ago

  • villassvj/Caco

    A reasoning-focused AI. optimized for epistemic honesty, safety, and human-aligned decision making. Designed to prioritize accuracy over creative embellishment and maintain transparency in uncertain contexts

    cloud

    128  Pulls 1  Tag Updated  4 months ago

  • vishalraj/dark-champion-21b

    tools

    89  Pulls 1  Tag Updated  7 months ago

  • vijayavp/medreason-qwen25-shortcot-exp2

    2  Pulls 1  Tag Updated  5 months ago

  • visharxd/coupon-generator

    tools

    2  Pulls 1  Tag Updated  1 year ago

© 2026 Ollama
Blog Support