Vision models · Ollama Search

qwen3-vl

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

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

58.3K Pulls 59 Tags Updated 3 days ago

mistral-small3.2

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

vision tools 24b

724.1K Pulls 5 Tags Updated 4 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

995.3K Pulls 17 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

351.5K Pulls 5 Tags Updated 6 months ago

llama4

Meta's latest collection of multimodal models.

vision tools 16x17b 128x17b

758.2K Pulls 11 Tags Updated 4 months ago

gemma3

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

vision 270m 1b 4b 12b 27b

23.6M Pulls 26 Tags Updated 2 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

421.7K Pulls 5 Tags Updated 8 months 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

2.8M Pulls 9 Tags Updated 5 months ago

minicpm-v

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

vision 8b

3.9M Pulls 17 Tags Updated 11 months ago

llava-phi3

A new small LLaVA model fine-tuned from Phi 3 Mini.

vision 3.8b

129.1K Pulls 4 Tags Updated 1 year ago

llava-llama3

A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.

vision 8b

2M Pulls 4 Tags Updated 1 year ago

moondream

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

vision 1.8b

386.7K Pulls 18 Tags Updated 1 year ago

bakllava

BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.

vision 7b

146.1K 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

11.2M Pulls 98 Tags Updated 1 year ago