Re:Microsoft strikes deal with Mistral in push beyond OpenAI
by dwaltrip on Monday February 26, 2024 @09:11PM
(#39519273)
Large LLMs like gpt-3 and gpt-4 need very serious hardware. They have hundreds of billions of parameters (or more) which need to be loaded in memory all at once.
[ Parent
| on HN ]
There are no comments on this comment yet.