Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
lostmsu
11 days ago
|
parent
|
context
|
favorite
| on:
Claude Code: connect to a local model when your qu...
If you are not planning to batch, you can run it much cheaper with Ryzen AI Max SoC devices.
Hell, if you are willing to go even slower, any GPU + ~80GB of RAM will do it.
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
Hell, if you are willing to go even slower, any GPU + ~80GB of RAM will do it.