consumer hardware is moving towards local ai and the models you can run now locally are already at opus 4.6 level. within 3 years most pc's sold will be ai computers.

This is true for the next 6 months if that.

The future is models baked into directly into hardware, onto bare metal, serving 10k+ tokens/sec.

We can have our little models, they'll be serving a different customer.

The cost and knowledge required to do that is not viable for the average consumer. Same reason the whole OpenClaw thing imploded.