Dedicated single-purpose hardware with models would be even less energy-intensive. It's theoretically possible to design chips which run neural networks and alike using just resistors (rather than transistors).
Such hardware is not general-purpose, and upgrading the model would not be possible, but there's plenty of use-cases where this is reasonable.
Such hardware is not general-purpose, and upgrading the model would not be possible, but there's plenty of use-cases where this is reasonable.