Are you observing higher tokens/second throughout on Apple silicon (you’ve been mentioning 20/second) than running it in PyTorch on a CUDA GPU such as a 3090?
I just look at the code and port it. I don't have the hardware to run it.
If you need extra hardware I'm sure the community could make that happen.
(20 tokens/second on a Mac is for the smallest model, ~5x smaller than 30B and 10x smaller than 65B)