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 treprinum on Monday February 19, 2024 @03:25PM (#39434372)
> Show me a 30b+ parameter model doing RAG as part of a conversation with voice responses in less than a second, running on Nvidia

I built one, should be live soon ;-)

[ Parent | on HN ]
Re:Groq runs Mixtral 8x7B-32k with 500 T/s by tome on Monday February 19, 2024 @03:47PM (#39434614)
Exciting! Looking forward to seeing it.
[ Parent | on HN ]