Much appreciated <3

Do you have a good resource for how one can go about this?

I would not recommend LocalAI. There documentation is somewhat lacking and it’s an all in one utility with many moving parts. The parts also tend to break, quite often.

I am currently migrating away from my 6th gen i5 to a newer N100.

Speed wise, it was about the same as the coral, about 6-8ms on the i5.

I have a similar setup and it’s been a huge pain when I when I have to do the OS updates.

The Coral needs a dkms module, but the sources and Google’s own documentation for it are out of date. I would highly recommend using the iGPU for inference.

That’s quite punny if you asked me.

I am pretty sure 2.5GBe will work over normal/standard CAT5 and Cat5e cable. It’s the upstream switch that you’ll need to replace.

I personally would stick to *sense. I personally used OPNSense there’s a huge community backing, well documented, and actively maintained. I like to use the CLI, but using the Web GUI was a breeze and I mainly wanted to set it and forget it.

There are a few 5x 2.5g N100 for $120-130 USD range on AliExpress. I grabbed one a while back for my own network.