Mistral Small 4 Collection A state-of-the-art model, open-weight, with a granular Mixture-of-Experts architecture that fuses instruct, reasoning and agentic skills. • 3 items • Updated about 7 hours ago • 26
Helios Collection Helios: 14B Real-Time Long Video Generation Model can be Cheaper, Faster but Keep Stronger than 1.3B ones • 7 items • Updated 1 day ago • 22
view article Article 🏟️ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do 7 days ago • 37
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 5 days ago • 114
Quantized Qwen3.5 Collection Verified models. Compatible with Transformers v5.3 and vLLM v0.16.1rc1 (nightly). Under evaluation. • 9 items • Updated 5 days ago • 9
💧 LFM2 Collection LFM2 is a new generation of hybrid models, designed for on-device deployment. • 28 items • Updated 3 days ago • 146
ParoQuant Collection Pairwise Rotation Quantization for Efficient Reasoning LLM Inference • 16 items • Updated 3 days ago • 12
BitDance Collection BitDance: Open-source autoregressive model with binary visual tokens. A research project for building powerful multimodal autoregressive model. • 10 items • Updated 15 days ago • 11
AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents Paper • 2602.06855 • Published Feb 6 • 77