Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
datadrivenangel
20 days ago
|
parent
|
context
|
favorite
| on:
Tinybox – A powerful computer for deep learning
Yeah I've got the q4 gpt-oss-120b running at ~40-60 tokens per second on an M5 Pro.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
