Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
losvedir
21 days ago
|
parent
|
context
|
favorite
| on:
Running local models on an M4 with 24GB memory
Datacenters are more efficient, though, because of batching.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
