Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
shwaj
on Aug 27, 2024
|
parent
|
context
|
favorite
| on:
Cerebras Inference: AI at Instant Speed
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...
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
https://groq.com/12-hours-later-groq-is-running-llama-3-inst...