macos implementation notes - fp32 on m1, maybe fp8 should just raise, use watermark env vars

https://github.com/comfyanonymous/ComfyUI/blob/19a64d62918c68b800de7277472c3b039beaa126/comfy/model_management.py#L1033

it's worth reading https://news.ycombinator.com/item?id=36576673

test fp32 versus fp16 versus bf16 on M1 macs, because there's no hardware bf16 support on M1. i don't know if apple's emulation on m1 actually provides memory or performance gains.

if the user tries to run an fp8 workflow, maybe raise because it is not supported on macos at all