https://arxiv.org/abs/2311.10770
"UltraFastBERT", apparently a variant of BERT, that uses only 0.3% of it's neurons during inference, is performing on par with similar BERT models.
I hope that's going to be available for all kinds of models in the near future!
I don't think so (unfortunately). The model size doesn't change, only the way it is traversed.