Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
tinyhouse
on April 17, 2024
|
parent
|
context
|
favorite
| on:
Mixtral 8x22B
Well, I don't have hardware to run a 141B parameters model, even if only 39B are active during inference.
navbaker
on April 17, 2024
[–]
It will be quantized in a matter of days and runnable on most laptops.
azinman2
on April 17, 2024
|
parent
[–]
8 bit is 149G. 4 bit is 80G.
I wouldn’t call this runnable on most laptops.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: