Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
layer8
6 months ago
|
parent
|
context
|
favorite
| on:
Qwen3 30B A3B Hits 13 token/s on 4xRaspberry Pi 5
I’d argue that chat is a time-sensitive application, and 13 tokens/s is significantly faster than I can read.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: