Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
ranger_danger
5 days ago
|
parent
|
context
|
favorite
| on:
How to run Qwen 3.5 locally
with regular llama.cpp on a 3070ti I get 60tok/s TG with the 9B model, it's quite impressive.
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
