vision · Ollama

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

2.6M Pulls 59 Tags Updated 5 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

195.9K Pulls 1 Tag Updated 2 months ago

deepseek-ocr

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

vision 3b

366.7K Pulls 3 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

1.6M Pulls 17 Tags Updated 10 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

675.1K Pulls 5 Tags Updated 11 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

13.5M Pulls 98 Tags Updated 2 years 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

4.2M Pulls 9 Tags Updated 10 months ago

minicpm-v

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

vision 8b

4.9M 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

844.7K 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

888.6K Pulls 18 Tags Updated 1 year ago

VisionVTAI/Aria-sama

tools

20 Pulls 1 Tag Updated 6 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

797.7K Pulls 50 Tags Updated 2 years ago

lukey03/qwen3.5-9b-abliterated-vision

vision tools thinking

9,806 Pulls 1 Tag Updated 3 weeks ago

sorc/qwen3.5-instruct-uncensored

Q8_0 Non-thinking Uncensored Non-Vision

tools 2b 4b 9b

2,630 Pulls 4 Tags Updated 2 weeks ago

fredrezones55/qwen3.5-opus

Qwen3.5-Claude-4.6-Opus-Reasoning-Distilled-v2; https://huggingface.co/Jackrong/; has vision properly merged and efficiently quantified.

vision tools thinking 4b 9b 27b

1,904 Pulls 4 Tags Updated 3 days ago

mdq100/qwen3.5-coder

Coding-optimized variants of the official Qwen3.5 MoE models — full vision capability retained, tuned for precise code generation via lower temperature. Based on Alibaba's Qwen3.5 distributed through the Ollama registry.

vision tools thinking 35b 122b

1,532 Pulls 2 Tags Updated 1 week ago

mdq100/qwen3.5-flash

A text-only, thinking-capable variant of Qwen3.5-35B-A3B — leaner and faster by removing the CLIP vision projector. Based on Unsloth's Q4_K_M quantization of Alibaba's Qwen3.5-35B-A3B.

tools thinking 35b

737 Pulls 2 Tags Updated 1 week ago

kiwi_kiwi/qwen3.5-abliterated-vision

vision tools thinking 9b

981 Pulls 1 Tag Updated 3 weeks ago

sorc/qwen3.5-uncensored

Q8_0 Uncensored Non-Vision

tools thinking 2b 4b 9b

730 Pulls 4 Tags Updated 2 weeks ago

Fermi/Cydonia-24B-v4.3-heretic-vision

A fork of coder3101/Cydonia-24B-v4.3-heretic-v3 (mradermacher's quant at Q4_K_M), with vision mmproj from bartowski/mistralai_Mistral-Small-3.2-24B-Instruct-2506-GGUF.

vision tools

243 Pulls 1 Tag Updated 2 weeks ago