Apple Silicon. But: there's no need to use the FP16 version. At 8-bit precision the quality loss is almost imperceptible. That cuts the footprint to 36GB. Which is great for a 64GB Mac, because you have room for plenty of context. 6-bit also works nicely at 26GB + context.

You want to use the newer quantization formats like Unsloth's UD quants or oQe, where the weights are selectively quantized using a calibration dataset so that important weights are left at/closer to full precision.

At 4 bit it easily fits in 32GB. That's what most people use.

use a quantized version. since it's MoE, what matters is that the 3b parameters that are used for every token fit in gpu vram, the rest can stay in system ram. really great if you don't have unified memory.