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. • 21 items • Updated 24 minutes ago • 49
view article Article GGML and llama.cpp join HF to ensure the long-term progress of Local AI +4 11 days ago • 471
MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration Paper • 2602.01734 • Published 28 days ago • 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. • 25 items • Updated about 4 hours ago • 4
Favorite Uncensored Drivers Collection These models have no refusals and require no jailbreaks • 24 items • Updated about 4 hours ago • 11
SVDQunat: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models Paper • 2411.05007 • Published Nov 7, 2024 • 24
Chatterbox Turbo Collection Ultra-Fast, Open-Source Text-to-Speech for Real-Time Voice AI • 3 items • Updated Dec 15, 2025 • 19
My models: daily driver rotation Collection A rotating list of models I created and currently use as daily drivers. From my many models, these are the ones I’m actively using. • 8 items • Updated 8 days ago • 6