Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
vision · Ollama
Search for models on Ollama.
  • qwen3-vl

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

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

    4.7M  Pulls 57  Tags Updated  8 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.

    vision tools thinking cloud

    368.2K  Pulls 1  Tag Updated  5 months ago

  • deepseek-ocr

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

    vision 3b

    497.3K  Pulls 3  Tags Updated  8 months 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

    14.4M  Pulls 98  Tags Updated  2 years ago

  • qwen2.5vl

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

    vision 3b 7b 32b 72b

    3.5M  Pulls 17  Tags Updated  1 year ago

  • 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

    4.9M  Pulls 9  Tags Updated  1 year ago

  • minicpm-v

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

    vision 8b

    5.3M  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

    950.8K  Pulls 5  Tags Updated  1 year 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

    766.3K  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

    1.5M  Pulls 18  Tags Updated  2 years ago

  • medgemma

    MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension.

    vision 4b 27b

    201.9K  Pulls 9  Tags Updated  3 months ago

  • VisionVTAI/Aria-sama

    tools

    29  Pulls 1  Tag Updated  10 months ago

  • openchat

    A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106.

    7b

    1.2M  Pulls 50  Tags Updated  2 years ago

  • numind/nuextract3

    NuExtract3 is a 4B vision-language reasoning model by NuMind for local document understanding. Turn text and document images into structured JSON or clean Markdown with Ollama, with support for multilingual documents, OCR, and template generation.

    vision tools thinking

    118  Pulls 4  Tags Updated  3 days ago

  • byczech/gemma4-it-mmproj-16G-Q3_K_S

    Gemma 4 31B multimodal instruct model with vision support, quantized to Q3_K_S and optimized for 16 GB VRAM. Supports a practical context window of approximately 36K–40K tokens, depending on the Ollama version, GPU, backend and runtime configuration.

    vision tools thinking 31b

    84  Pulls 1  Tag Updated  6 days ago

  • Barbatos/gemfable-agent

    Agentic coding model for 24 GB GPUs: TeichAI's Gemma-4-31B Fable-5 agent distill (vision + thinking + tools) with a disciplined coding-agent system prompt baked in. Inspect → reproduce → smallest fix → re-verify.

    vision tools thinking 31b

    66  Pulls 1  Tag Updated  6 days ago

  • oamazonasgabriel/qwen3.5-2b

    Qwen3.5 2B in Q8_0 quantization. Strong balance of capability and efficiency with 262K context, vision, tool use, and thinking. Ideal for local deployment on consumer hardware.

    vision tools thinking

    37  Pulls 1  Tag Updated  3 days ago

  • oamazonasgabriel/qwen3.5-0.8b

    Qwen3.5 0.8B in Q8_0 quantization. Small, fast model with 262K context, vision, tool use, and thinking capabilities. Optimized for local/edge deployment on constrained hardware.

    vision tools thinking

    21  Pulls 1  Tag Updated  3 days ago

  • aratan/Ollama-Agent

    Ollama Agent + Skills + Vision 26 t/s en 8 VRAM 2026

    vision tools

    5  Pulls 1  Tag Updated  2 days ago

  • jordimurgo/medgemma1.5-thinking

    MedGemma 1.5 4.3B Q4_K_M with native Ollama thinking separation, vision support, deterministic decoding, and unchanged official weights and tokenizer.

    vision thinking

    4  Pulls 1  Tag Updated  19 hours ago

© 2026 Ollama
Blog Contact