Depends on which variant you pull down, but a single 5090 GPU (I know these are insanely expensive, but for context) could run either the Q8 or Q4_K_M version. It will not fit the 52GB version (BF16) on the other hand. So any modern Mac with a Pro or better processor and more than 52GB of RAM (don't forget VRAM for context window also matters!) would suffice, as someone else noted, probably a 128GB model would do the trick, and give you enough wiggle room to max out the context window.
My Mac only has 16GB of VRAM (20GB total - 8 is reserved for the OS) so I have to leave room for VRAM, I usually find a model that fits in 5 to 7 GB of VRAM and then max the context window as much as I can.
The benefit of running the full precision version is negligible (probably not even measurable above the benchmark noise floor). Most common for cost-conscious users is to run something around 4-6 bits per weight, which would fit on a 24 or 32 GB card (as you mentioned).
Oh man! I had no idea I could do this at all! What do you usually tweak it to? I feel like 8 GB is probably still a reasonable amount to give the rest of the OS.
I recommend MacBook M5 Max with 128 GB of RAM to run it comfortably and fast. If you have something like a regular M4, go with qwen3.6-35b-a3d - the Mixture of Expert architecture makes it run 2-3x faster than the 27b version.
I bought r9700 for about 1700-1800$ and I have like 800t/s prompt and about 50t/s of inference on average? It hurt a bit when you change a prompt so llama.cpp have to discard entire cache and it have to think for 2-5min depending on the context, but otherwise it is faster than I can read.
My Mac only has 16GB of VRAM (20GB total - 8 is reserved for the OS) so I have to leave room for VRAM, I usually find a model that fits in 5 to 7 GB of VRAM and then max the context window as much as I can.