LFM3-VL-2B is a vision-language model for on-device visual understanding.
Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.
Bonsai 2 from Prism ML is a family of vision models built for ternary weights – smaller models with close to full-precision quality.
Nemotron 3.5 Bolt is NVIDIA’s compact vision-language model for local coding, reasoning, and tool use.
Nemotron 3.5 Super is NVIDIA’s vision-language model for coding, reasoning, tool use, and document understanding
DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.
The most powerful vision-language model in the Qwen model family to date.
Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.
🌋 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.
A series of multimodal LLMs (MLLMs) designed for vision-language understanding.
moondream2 is a small vision language model designed to run efficiently on edge devices.
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.
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.
NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.
An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.
fine-tuned model on Linux Command Library (https://linuxcommandlibrary.com/basic/oneliners)
9B distilled from DeepSeek-V4-Pro: decensored, with thinking, tool calling and vision in one checkpoint. q4km 6.25GB · q6k 7.98GB · q8_0 10.15GB · f16 18.84GB.
DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.
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.
Uncensored version of qwen 2.5