Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
fsiefken
42 days ago
|
parent
|
context
|
favorite
| on:
Qwen3-Max-Thinking
I can confirm, running glm-4.7-flash-7e-qx54g-hi-mlx here, a 22gb model @q5 on m4 max pro and 59 tokens/s.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
