Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
mhitza
9 months ago
|
parent
|
context
|
favorite
| on:
Open models by OpenAI
That M4 Max is really something else, I get also 70 tokens/second on eval on a RTX 4000 SFF Ada server GPU.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
