For just the model itself: 4 x params at F32, 2 x params at F16/BF16, or 1 x params at F8, e.g. 685GB at F8. It will be smaller for quantizations, but I'm not sure how to estimate those.
For a Mixture of Experts (MoE) model you only need to have the memory size of a given expert. There will be some swapping out as it figures out which expert to use, or to change expert, but once that expert is loaded it won't be swapping memory to perform the calculations.
You'll also need space for the context window; I'm not sure how to calculate that either.
alt Hacker News
For just the model itself: 4 x params at F32, 2 x params at F16/BF16, or 1 x params at F8, e.g. 685GB at F8. It will be smaller for quantizations, but I'm not sure how to estimate those.
For a Mixture of Experts (MoE) model you only need to have the memory size of a given expert. There will be some swapping out as it figures out which expert to use, or to change expert, but once that expert is loaded it won't be swapping memory to perform the calculations.
You'll also need space for the context window; I'm not sure how to calculate that either.