I'm curious why not. I am running a few different models on my mac studio. I'm u... | Hacker News

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

		kevin42 5 months ago \| parent \| context \| favorite \| on: Apple M3 Ultra I'm curious why not. I am running a few different models on my mac studio. I'm using llama.cpp, and it performs amazingly fast for the $7k I spent.

behnamoh 5 months ago [–]

I said in parallel.

saagarjha 5 months ago | [–]

Surely you can run smaller models together

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