🚀 Qwen-MTP Collection ⚡ MTP (Multi Token Prediction) speculative decoding enables models like Qwen3.6 to have ~1.4-2.2x faster generation with no change in accuracy. • 9 items • Updated 28 days ago • 34
🍎 Qwopus3.6 Collection This collection features the advanced Qwopus3.6 series of multimodal large models, which are fine-tuned from the Qwen3.6 base models with a focus on e • 8 items • Updated 26 days ago • 76
💻 Qwopus-Coder Collection Reasoning-distilled coding models optimized for specialized domains like agentic workflows. • 10 items • Updated 26 days ago • 46
💧 LFM2.5 Collection Collection of post-trained and base LFM2.5 models. • 14 items • Updated Jun 25 • 180