ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference Paper • 2511.10645 • Published Nov 13, 2025 • 7
ParoQuant Collection Pairwise Rotation Quantization for Efficient Reasoning LLM Inference • 15 items • Updated 2 days ago • 10
Eagle Collection Eagle is a family of frontier vision-language models with data-centric strategies. The model supports both HD image and long-context video input. • 14 items • Updated 1 day ago • 40
Qwen3.5 Collection Qwen3.5 is Qwen's new model family including Qwen3.5 Small: 0.8B, 2B, 4B, 9B and Qwen3.5 Medium: 35B-A3B, 27B, 122B-A10B and 397B-A17B. • 25 items • Updated 1 day ago • 112
view article Article GGML and llama.cpp join HF to ensure the long-term progress of Local AI +4 21 days ago • 483
MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration Paper • 2602.01734 • Published Feb 2 • 32
DFloat11 | FLUX.1 Collection Losslessly compressed FLUX.1: requires < 20GB VRAM to run. • 6 items • Updated Jul 5, 2025 • 2
Favorite Models Collection Models with that certain something. Non-exhaustive list, no particular order. • 21 items • Updated 6 days ago • 4
Favorite Uncensored Drivers Collection These models have no refusals and require no jailbreaks • 28 items • Updated 8 days ago • 13
SVDQunat: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models Paper • 2411.05007 • Published Nov 7, 2024 • 24