The numbers are pretty incredible. Will the competition be able to match them? | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		smsx on Aug 27, 2024 \| parent \| context \| favorite \| on: Cerebras Inference: AI at Instant Speed The numbers are pretty incredible. Will the competition be able to match them?

shwaj on Aug 27, 2024 | [–]

Groq is claiming 284 tokens/second on Llama 3.1 70b, so they’re in the same ballpark.

https://groq.com/12-hours-later-groq-is-running-llama-3-inst...

wmf on Aug 27, 2024 | [–]

If Groq 2 is 2x faster it will match Cerebras WSE-3.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact