$ orca models pull llama-3.1-70b
Fetching manifest... done
Loading onto local GPU... done
$ orca serve --model llama-3.1-70b
Listening on orca.local:11434
$
Built for local AI
Your AI server.
Your AI server.
Zero cloud.
Every Orca ships pre-configured and ready to run. Plug it in, connect from any device, and deploy models in minutes.
Get early access