Burning weights onto a chip in an efficient way and exposing that via USB would be acceptable for a good enough model tbh

This is pretty close to what Taalas is doing.

	▲	calgoo 2 hours ago \| parent [-]
		Trying Taalas is almost scary, there is something unsettling with that speed! Even with that small model, because of the speed, you could run hundreds of sample runs in a second, and pick from the best. Can't wait for their next release!