News for hackers. Stuff that matters.

A comment on Running a 180B parameter LLM on a single Apple M2 Ultra. Parent comment

Re:Running a 180B parameter LLM on a single Apple M2 Ultra by noiv on Thursday September 07, 2023 @04:12PM (#37424918)
RAM may be growing, but free and acceptable content to train models isn't.

Question is which is the last model one might install to satisfy all needs.

[ Parent | on HN ]

There are no comments on this comment yet.