Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
qumpis
on March 12, 2023
|
parent
|
context
|
favorite
| on:
Large language models are having their Stable Diff...
What's your ram usage for this?
JoeMattie
on March 12, 2023
|
next
[–]
I've got the (4-bit quantized) 65B param model running at somewhat acceptable speed on an i9-7900. It uses around 55GB of RAM.
ddren
on March 12, 2023
|
prev
[–]
The (quantized) 13B model is 7.6 GB on disk and the program uses around 8 GB to run. It runs without hitting the swap with just 9 GB assigned to WSL2.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: