Y
Hacker News
new
|
ask
|
show
|
jobs
by
throw1234567891
6 days ago
You don’t need a datacenter. 1T model requires 1T of RAM. Not easy to come by today in a compact factor but nowhere near the datacenter.
1 comments
nullc
5 days ago
> 1T model requires 1T of RAM
assuming 8 bits per weight, but 4bits is commonly used once you get to that scale.
link
assuming 8 bits per weight, but 4bits is commonly used once you get to that scale.