Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.
5.2M Pulls 9 Tags Updated 1 year ago
The most powerful vision-language model in the Qwen model family to date.
5.8M Pulls 57 Tags Updated 10 months ago
DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.
527.5K Pulls 3 Tags Updated 9 months ago
Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.
4.8M Pulls 17 Tags Updated 1 year 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.
14.8M Pulls 98 Tags Updated 2 years ago
A series of multimodal LLMs (MLLMs) designed for vision-language understanding.
5.4M 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.
993.4K Pulls 5 Tags Updated 1 year ago
moondream2 is a small vision language model designed to run efficiently on edge devices.
1.8M Pulls 18 Tags Updated 2 years 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.
785.7K Pulls 5 Tags Updated 1 year ago
NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.
81.3K Pulls 1 Tag Updated 3 months ago
An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.
145.8K Pulls 3 Tags Updated 5 months ago
fine-tuned model on Linux Command Library (https://linuxcommandlibrary.com/basic/oneliners)
401 Pulls 1 Tag Updated 1 year ago
29 Pulls 1 Tag Updated 1 year ago
DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.
385.1K Pulls 2 Tags Updated 3 weeks ago
Local-first AI tool router. 2B/4B/9B read images (vision); 27B text-only. 14B/32B retired. 99.1-100% routing accuracy (BFCL). 97% of traffic stays local.
1,896 Pulls 6 Tags Updated 3 weeks ago
Uncensored version of qwen 2.5
297 Pulls 1 Tag Updated 5 months ago
A reasoning-focused AI. optimized for epistemic honesty, safety, and human-aligned decision making. Designed to prioritize accuracy over creative embellishment and maintain transparency in uncertain contexts
128 Pulls 1 Tag Updated 4 months ago
89 Pulls 1 Tag Updated 7 months ago
2 Pulls 1 Tag Updated 5 months ago
2 Pulls 1 Tag Updated 1 year ago