Llama.cpp can do 40 tok/s on M2 Max, 0% CPU usage, using all 38 GPU cores
by from on (#6C1Y5)
External Content
| Source | RSS or Atom Feed |
| Feed Location | http://news.ycombinator.com/rss |
| Feed Title | |
| Feed Link | http://news.ycombinator.com/ |
| Reply | 0 comments |