Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
mdz4040
6 months ago
|
parent
|
context
|
favorite
| on:
Open models by OpenAI
55 token/s here on m4 pro, turning on flash attention puts it to 60/s.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
