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 easygenes on Thursday September 07, 2023 @12:58PM (#37421962)
Depending on the task, the best open models will outperform GPT-3.5, but would be more expensive to run at comparable speed. GPT-4 is in a league of its own.
[ Parent | on HN ]

There are no comments on this comment yet.