News for hackers. Stuff that matters.

A comment on GPT-4 Details Leaked. Parent comment

Re:GPT-4 Details Leaked by snowycat on Tuesday July 11, 2023 @02:01PM (#36684786)
I am running 30b llama models (4 bit quantized using llama.cpp) on 32 gb of ram and no GPU. I get around 2 tokens/second.
[ Parent | on HN ]

There are no comments on this comment yet.