LLaMa [1] works on Apple Mx processors due to unified memory. The 7B model works on a 8GB Apple MacBook Pro M1, ~40 seconds/token.
[1] https://dev.l1x.be/posts/2023/03/12/using-llama-with-m1-mac
[1] https://dev.l1x.be/posts/2023/03/12/using-llama-with-m1-mac