A simple equation to approximate it is `memory_in_gb = parameters_in_billions * (bits/8)`
So at 32 bit full precision, 70 * (32 / 8) ~= 280GB
fp16, 70 * (16 / 8) ~= 140GB
8 bit, 70 * (8 / 8) ~= 70GB
4 bit, 70 * (4 / 8) ~= 35GB
However in things like llama.cpp quants sometimes it's mixed so some of the weights are Q5, some Q4, etc, so you usually want to take the higher number.
So at 32 bit full precision, 70 * (32 / 8) ~= 280GB
fp16, 70 * (16 / 8) ~= 140GB
8 bit, 70 * (8 / 8) ~= 70GB
4 bit, 70 * (4 / 8) ~= 35GB
However in things like llama.cpp quants sometimes it's mixed so some of the weights are Q5, some Q4, etc, so you usually want to take the higher number.