lpu on Hacker News: 1 stories with screenshots

Screenshot of groq.com: Groq runs Mixtral 8x7B-32k with 500 T/s

Groq runs Mixtral 8x7B-32k with 500 T/s (groq.com)

739 points by tin7in 2 years ago | 431 comments

Groq's homepage, showcasing its fast LLM inference service running Mixtral 8x7B at around 500 tokens per second; the capture shows only a logo splash.

groq mixtral llm-inference lpu

#lpu on Hacker News

Groq runs Mixtral 8x7B-32k with 500 T/s(groq.com)

Groq runs Mixtral 8x7B-32k with 500 T/s (groq.com)