Qwen3.5 Dense-to-MoE Weight Transfer Collection Qwen3.5 MoE models from dual-source weight transfer (dense backbone + 35B-A3B experts). Hybrid DeltaNet + GQA attention. โข 6 items โข Updated Mar 4 โข 1
๐ป Local SmolLMs Collection SmolLM models in MLC, ONNX and GGUF format for local applications + in-browser demos โข 14 items โข Updated May 5, 2025 โข 59
view article Article CodeGemma - an official Google release for code LLMs +4 pcuenq, osanseviero, reach-vb, philschmid, mishig, loubnabnl โข Apr 9, 2024 โข 107