Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Mistral NeMo. Parent comment
A 12B model will run on a 4090 with plenty room to spare, even with 8-bit quantisation.
There are no comments on this comment yet.
A 12B model will run on a 4090 with plenty room to spare, even with 8-bit quantisation.