Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
netdur
29 days ago
|
parent
|
context
|
favorite
| on:
Accelerating Gemma 4: faster inference with multi-...
I am getting 21 t/s on Fold 7, 21 x 1.8 = 37.8 t/s compared to M1 Max's 54 t/s, that is impressive
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: