For LLM models, TheBloke has provided memory requirements for all of their quantisations. For Apple Silicon you want to look at the GGUF models.

Here's Mixtral-8x7B-Instruct: https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-G...

64GB of memory will struggle on 65-70B (or bigger) models, and you'll be limited to running 70B on Q3 or Q4 if you want to use it somewhat comfortably.

I’m not sure, not really an expert in this field, just casually interested as an outsider. When I bought my Mac, 64 was as high as you could go.