How large are large language models?

How big are those in terms of size on disk and VRAM size?

Something like 1.61B just doesn't mean much to me since I don't know much about the guts of LLMs. But I'm curious about how that translates to computer hardware -- what specs would I need to run these? What could I run now, what would require spending some money, and what I might hope to be able to run in a decade?

At 1byte/param that's 1.6GB (f8), at 2 bytes (f16) that's 2.3GB -- but there's other space costs beyond loading the parameters for the GPU. So a rule of thumb is ~4x parameter count. So round up, 2B -> 2*4 = 8GB VRAM