That's a good ballpark for something quantized to 8 bits per parameter. But you can 2x/4x that for 16 and 32 bit.
I've never seen a 32 bit model. There's bound to be a few of them, but it's hardly a normal precision.
alt Hacker News
I've never seen a 32 bit model. There's bound to be a few of them, but it's hardly a normal precision.