News for hackers. Stuff that matters.

A comment on Groq runs Mixtral 8x7B-32k with 500 T/s. Parent comment

Re:Groq runs Mixtral 8x7B-32k with 500 T/s by jrflowers on Tuesday February 20, 2024 @12:33AM (#39438359)
>Show me a 30b+ parameter model doing RAG as part of a conversation with voice responses in less than a second, running on Nvidia.

Is your version of that on a different page from this chat bot?

[ Parent | on HN ]

There are no comments on this comment yet.