Unsloth AI
@UnslothAI
Train and run models locally! 🦥
参加 November 2023
480 フォロー中 88.9K ファン
Gemma 4 now runs 2x faster with MTP GGUFs! Run locally on just 6GB RAM. ⚡️
MTP enables Google Gemma 4 run ~1.4–2.2× faster with no accuracy loss.
Gemma 4 12B MTP can run at 162 t/s vs. 52 t/s without MTP. 31B reaches 101 t/s.
GGUFs + Guide:
もっと見る
