Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Tepix
on March 13, 2023
|
parent
|
context
|
favorite
| on:
Llama.cpp: Port of Facebook's LLaMA model in C/C++...
Are you sure? I think it took a mere 2 hours to do 4bit GPTQ quantization of LLaMA-65B on 1x RTX 3090. But i may be mistaken.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
