Unsloth AI (@UnslothAI) “Qwen3.6 now runs 2x faster with MTP GGUFs! Run locally on just 18GB RAM. ⚡️ MTP” — TopicDigg
Unsloth AI
@UnslothAI
Train and run models locally! 🦥
加入 November 2023
473 正在关注 64.9K 粉丝
Qwen3.6 now runs 2x faster with MTP GGUFs! Run locally on just 18GB RAM. ⚡️
MTP enables Qwen3.6 to generate ~1.4–2.2× faster with no accuracy change.
Qwen3.6-27B MTP runs at 160 tokens/s. 35B-A3B reaches 240 t/s.
GGUFs:
Guide:
显示更多
