Hacker News new | ask | show | jobs
by smsx 655 days ago
The numbers are pretty incredible. Will the competition be able to match them?
2 comments
shwaj 655 days ago
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...

link
wmf 654 days ago
If Groq 2 is 2x faster it will match Cerebras WSE-3.
link