Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
mrtksn
on March 11, 2023
|
parent
|
context
|
favorite
| on:
Llama.cpp: Port of Facebook's LLaMA model in C/C++...
You can, I was able to run 13B on my 16GB 8c8g M1 Air. The performance was 2-3 tokens/second. It felt on par with ChatGPT on a busy day.
Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
