Publish a model Sign in Create account

Community model & dataset hub

Stop renting intelligence.

Run models on hardware you control. No API key, no per-token bill, no cloud dependency. Structured reviews and enforced documentation are how you tell which ones are actually worth running.

Start with the task

Text generation Embeddings Speech recognition Vision-language Other Fill-mask Image classification Text classification

15 models · Vision-language · All licences · base

Highest rated Most reviewed Newest

Rank by dimensionAccuracy Fine-tune Docs Speed

Qwen/Qwen3-VL-8B-Instruct

Documentation incomplete.

Vision-languageapache-2.0

Qwen/Qwen2.5-VL-7B-Instruct

Documentation incomplete.

Vision-languageapache-2.0

Qwen/Qwen3.8-27B

Documentation incomplete.

Vision-languageapache-2.0

Qwen/Qwen3.6-27B

Documentation incomplete.

Vision-languageapache-2.0

Qwen/Qwen3-VL-4B-Instruct

Documentation incomplete.

Vision-languageapache-2.0

Qwen/Qwen3.6-35B-A3B

Documentation incomplete.

Vision-languageapache-2.0

Qwen/Qwen2.5-VL-3B-Instruct

Documentation incomplete.

Vision-language—

Qwen/Qwen3-VL-2B-Instruct

Documentation incomplete.

Vision-languageapache-2.0

datalab-to/chandra-ocr-2

Documentation incomplete.

Vision-languageopenrail

microsoft/Florence-2-base

Documentation incomplete.

Vision-languagemit

baidu/Unlimited-OCR

Documentation incomplete.

Vision-languagemit

HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive

Documentation incomplete.

Vision-languagegemma

deepseek-ai/DeepSeek-OCR

Documentation incomplete.

Vision-languagemit

moonshotai/Kimi-K3

Documentation incomplete.

Vision-languageother

Qwen/Qwen3.5-27B

Documentation incomplete.

Vision-languageapache-2.0