🚀 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 about 4 hours ago • 29
💻 Qwopus-Coder Collection Reasoning-distilled coding models optimized for specialized domains like agentic workflows. • 10 items • Updated about 4 hours ago • 27
Jackrong/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF Image-Text-to-Text • 27B • Updated about 4 hours ago • 1.38k • 18