🚀 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. • 7 items • Updated 5 days ago • 26
Brian6145/Qwen3.6-27B-Claude-Opus-Sonnet-DistilledV2-MTP-GGUF Text Generation • 27B • Updated 28 days ago • 11.2k • 12
Running Featured 1.05k Can You Run It? LLM version 🚀 1.05k Check if your GPU can run a chosen LLM model