Unsloth AI
@UnslothAI
Train and run models locally! 🦥
加入 November 2023
480 正在关注 88.9K 粉丝
We’re releasing new Qwen3.6 quants that run 2.5× faster on your GPU.
Qwen3.6-27B NVFP4 runs on 24GB VRAM.
35B-A3B can hit 17,561 tok/s (B200).
We also improved accuracy, tool calling, agent use, and looping.
Guide:
Qwen3.6 NVFP4:
显示更多
