You should be able to run smaller models on an M1. I'm testing this in about 10m... | Hacker News

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

		wsgeorge 11 months ago \| parent \| context \| favorite \| on: DeepSeek-R1 You should be able to run smaller models on an M1. I'm testing this in about 10mins

ionwake 11 months ago [–]

how did it go wsgeorge? is there like a 10 second pause between each word when running on a Mac? I thought I could only run 8b models on it from what I remember last year and even those were super slow!

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