The M1 is (supposedly) specialized for ML calculations and on a decidedly denser node, though. I guess it's a testament to either CUDA's power or machine learning GPGPU optimization.
It is, but they’re not using any of that. Only the M1 GPU at this time.
//part of nod.ai / SHARK team.
https://timdettmers.com/2020/09/07/which-gpu-for-deep-learni...
It seems that their consumer GPUs also have a gap