GPU-Allocatable VRAM

On a unified-memory box, GPU-allocatable VRAM is the slice of the shared RAM pool the graphics processor is allowed to treat as video memory. AMD's Ryzen AI Max+ 395 boxes ship 128GB of LPDDR5X and let you assign up to 96GB of it to the GPU — the headroom that loads 70B-class and larger models. The rest stays reserved for the CPU and OS. It's a firmware/driver setting, not a fixed hardware limit, which is why the same 128GB box can be configured for more or less GPU memory.

This is the number that decides what model actually fits, and it's smaller than the total RAM — a 128GB box gives you ~96GB of usable VRAM, not 128GB. Size your model against the allocatable figure, not the sticker capacity.