The support is bad for custom nodes and NPUs are fairly slow compared to GPUs (expect 5x to 10x longer generation time compared to 30xx+ GPUs in best case scenarios) NPUs are good at running small models efficiently, not large LLM / Image models.

Most website do not run on servo

I use obtainium to install it and it works flawlessly. The reason they don’t publish it elsewhere is due to licences and push notifications iirc

https://anubis.techaro.lol/docs/user/known-broken-extensions

If you have JShelter installed, it breaks the proof of work from anubis