I've played with https://github.com/jasperproject in the past to create a vocal assistant on my Ubuntu 22 box, and have been thinking about build a connector to ollama's REST API... didn't know if anyone had already combined the two.
I mean, they get distributed over multiple GPU cores... what's it matter if they're local or not?
I mean, they get distributed over multiple GPU cores... what's it matter if they're local or not?