News for hackers. Stuff that matters.
Re:Nvidia buying AI chip startup Groq for about $20B by LoganDark on Wednesday December 24, 2025 @07:04PM (#46380715)
For inference, but yes. Many hundreds of tokens per second of output is the norm, in my experience. I don't recall the prompt processing figures but I think it was somewhere in the low hundreds of tokens per second (so slightly slower than inference).

There are no comments on this comment yet.