Qwen3.5 Collection Qwen3.5 is Qwen's new model family including Qwen3.5-35B-A3B, 27B, 122B-A10B and 397B-A17B. • 10 items • Updated 1 day ago • 29
ColBERT-Zero 🐶 Collection First large-scale fully pre-trained ColBERT model using only public data, outperforming GTE-ModernColBERT and GTE-ModernBERT • 10 items • Updated 7 days ago • 16
Tiny-A2D Collection Small diffusion language models adapted from AR models • 4 items • Updated Dec 6, 2025 • 16
DFlash Collection Block Diffusion for Flash Speculative Decoding • 7 items • Updated about 12 hours ago • 18
view article Article Aligning to What? Rethinking Agent Generalization in MiniMax M2 Oct 30, 2025 • 43
Ministral 3 Collection A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated Dec 2, 2025 • 155
Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence Paper • 2511.07384 • Published Nov 10, 2025 • 19
view article Article What’s MXFP4? The 4-Bit Secret Powering OpenAI’s GPT‑OSS Models on Modest Hardware Aug 8, 2025 • 33
💧 LFM2 Collection LFM2 is a new generation of hybrid models, designed for on-device deployment. • 31 items • Updated 2 days ago • 142