Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
turnsout
on May 1, 2025
|
parent
|
context
|
favorite
| on:
Running Qwen3 on your macbook, using MLX, to vibe ...
I believe mlx will allow you to run the models marginally faster (per a recent blog post by @simonw)
simonw
on May 1, 2025
[–]
Yeah, you don't necessarily
need
it but it's optimized for Apple Silicon and in my experience feels like it gives slightly better performance than GGUFs. I really need to formally measure that so I'm not just running on vibes!
indigodaddy
on May 1, 2025
|
parent
[–]
I for one, am willing to just trust you bro ;)
turnsout
on May 1, 2025
|
root
|
parent
[–]
Yeah I’ll go with Simon’s vibes over most people’s measurements!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: