Hacker News new | ask | show | jobs
by zozbot234 46 days ago
4-bit quantization is native for Kimi 2.x series.
1 comments
CamperBob2 46 days ago
You're right, I was thinking of Qwen. K2.6 will run at UD-Q2_K_XL precision on 4x RTX6000 boards, but I have no idea if it's worthwhile.
link