Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.
4.5M Pulls 9 Tags Updated 1 year ago
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.
292.4K Pulls 1 Tag Updated 3 months ago
The most powerful vision-language model in the Qwen model family to date.
3.9M Pulls 59 Tags Updated 6 months ago
DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.
449.7K Pulls 3 Tags Updated 6 months ago
🌋 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.
14.1M Pulls 98 Tags Updated 2 years ago
A series of multimodal LLMs (MLLMs) designed for vision-language understanding.
5.2M Pulls 17 Tags Updated 1 year ago
Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.
2M Pulls 17 Tags Updated 1 year ago
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.
913.6K Pulls 5 Tags Updated 1 year ago
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.
743.9K Pulls 5 Tags Updated 1 year ago
moondream2 is a small vision language model designed to run efficiently on edge devices.
1.2M Pulls 18 Tags Updated 2 years ago
An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.
117.4K Pulls 3 Tags Updated 2 months ago
22 Pulls 1 Tag Updated 8 months ago
fine-tuned model on Linux Command Library (https://linuxcommandlibrary.com/basic/oneliners)
374 Pulls 1 Tag Updated 1 year ago
DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a 1M-token context window and three reasoning modes.
70.8K Pulls 1 Tag Updated 3 weeks ago
DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance.
2.2M Pulls 1 Tag Updated 5 months ago
A reasoning-focused refinement of gemma4:31B, optimized for epistemic honesty, safety, and human-aligned decision making. Designed to prioritize factual accuracy over creative embellishment and maintain transparency in uncertain contexts.
54 Pulls 1 Tag Updated 3 weeks ago
Uncensored version of qwen 2.5
199 Pulls 1 Tag Updated 2 months ago
57 Pulls 1 Tag Updated 3 months ago
2 Pulls 1 Tag Updated 1 month ago
2 Pulls 1 Tag Updated 1 year ago