logoalt Hacker News

omneitytoday at 5:07 AM0 repliesview on HN

It’s a trivial calculation to make (+/- 10%).

Number of params == “variables” in memory

VRAM footprint ~= number of params * size of a param

A 4B model at 8 bits will result in 4GB vram give or take, same as params. At 4 bits ~= 2GB and so on. Kimi is about 512GB at 4 bits.