Comment by nullc
1 day ago
> 1T model requires 1T of RAM
assuming 8 bits per weight, but 4bits is commonly used once you get to that scale.
1 day ago
> 1T model requires 1T of RAM
assuming 8 bits per weight, but 4bits is commonly used once you get to that scale.
No comments yet
Contribute on Hacker News ↗