Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
hnfong
on April 18, 2024
|
parent
|
context
|
favorite
| on:
Meta Llama 3
With quantized models you can run 70B models on 64GB RAM comfortably.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
