view article Article ποΈ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do 3 days ago β’ 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. β’ 25 items β’ Updated 1 day ago β’ 112
Quantized Qwen3.5 Collection Verified models. Compatible with Transformers v5.3 and vLLM v0.16.1rc1 (nightly). Under evaluation. β’ 9 items β’ Updated about 19 hours ago β’ 9
π§ LFM2 Collection LFM2 is a new generation of hybrid models, designed for on-device deployment. β’ 28 items β’ Updated 11 days ago β’ 146
ParoQuant Collection Pairwise Rotation Quantization for Efficient Reasoning LLM Inference β’ 15 items β’ Updated 3 days ago β’ 10
Tiny Aya Collection Bridging Scale and Multilingual Depth β’ 10 items β’ Updated 24 days ago β’ 64
BitDance Collection BitDance: Open-source autoregressive model with binary visual tokens. A research project for building powerful multimodal autoregressive model. β’ 10 items β’ Updated 11 days ago β’ 11
LLaDA2.1: Speeding Up Text Diffusion via Token Editing Paper β’ 2602.08676 β’ Published Feb 9 β’ 70
AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents Paper β’ 2602.06855 β’ Published Feb 6 β’ 75
ComfyUI-native DF11 models Collection Note: Only Flux-dev based models work with the official DF11 custom node out-of-the-box. The rest require my custom fork, or patching to work. β’ 37 items β’ Updated 3 days ago β’ 8