HN
Hacker News
Top
New
Best
Ask
Show
Jobs
Comment by vorticalbox | Hacker News Reader
Parent
Full thread
vorticalbox
·
Have you looked at using oMLX?
https://omlx.ai/
View on HN
mc8098
·
Would second this, I switched to oMLX I get ~75 tok/s on Qwen3.6-35B-A3B-4bit on a 48GB M5 Pro
Reply on news.ycombinator.com