News for hackers. Stuff that matters.
Re:Running large language models like ChatGPT on a single GPU by nathan_compton on Monday February 20, 2023 @04:07PM (#34872915)
It is entirely possible to run 6.7B parameter models on a 3090, although I believe you need 16 bit weights. I think you can squeeze a 20b parameter model onto the 3090 if you go all the way down to 8.

There are no comments on this comment yet.