Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
nullc
20 days ago
|
parent
|
context
|
favorite
| on:
GLM-5.2 – How to Run Locally
Just running cpu only w/ Q6 on 9684X I get about 1tok/s ... also still get about 1tok/s/stream when running 16 in parallel.
nullc
19 days ago
[–]
6.5t/s if I add one RTX R6000 gpu (where is uses about 25GB).
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: