I only get ~4 tok/sec on a M1 Pro with MTP. | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

quinncom 23 days ago | parent | context | favorite | on: Ornith-1.5: From Self-Scaffolding to Self-Improvem...

I only get ~4 tok/sec on a M1 Pro with MTP.

regexorcist 23 days ago [–]

I get ~10 tok/sec on a M1 Ultra, but the real issue is abysmal prompt processing which makes it unusable. On the M1 and M2 series MTP is actively harmful for performance.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact