Haven’t heard about it. I probably should give it a try.

Downtime is the friends made along the way

Got it, makes sense. You’d probably have to do some benchmarking first. Depending on how large the source catalog is.

So you’re using CPU offloading? Or the model’s Bonsai2 variation?

Why wouldn’t you trust a local model? I mean sure they are less intelligent but if you dont expose it publicly you should be good to go

I just bought a 32GB M6 Mac Mini that I’ll also use for local ai. Will probably use Qwen3.8-27B. Accessing it from outside my lan would happen via Tailscale.

DNS blockers work so why would I need your solution? I dont care if the sites try to reconnect cause the connection wont work nonetheless

Nowadays the internet is pretty much unusable without ad blockers/dns sinkholes