30 tok/s generation? Nice! What was prefill by the way? Also, these are 256 GB R... | Hacker News

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

arjie 34 days ago | parent | context | favorite | on: Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac...

30 tok/s generation? Nice! What was prefill by the way? Also, these are 256 GB RAM studios? Good timing on those!

sh3rl0ck 31 days ago [–]

512 GB!

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