Navigation
Search
|
AMD predicts future AI PCs will run 30B parameter models at 100 tokens per second
Monday July 15, 2024. 03:01 PM , from TheRegister
They're gonna need a heck of a lot of memory bandwidth – not to mention capacity – to do it
Analysis Within a few years, AMD expects to have notebook chips capable of running 30-billion-parameter large-language models locally at a speedy 100 tokens per second.…
https://go.theregister.com/feed/www.theregister.com/2024/07/15/amd_ai_pc_goal/
Related News |
25 sources
Current Date
Nov, Tue 5 - 07:38 CET
|