this post was submitted on 25 Jul 2024
654 points (100.0% liked)

196

16431 readers
1698 users here now

Be sure to follow the rule before you head out.

Rule: You must post before you leave.

^other^ ^rules^

founded 1 year ago
MODERATORS
 
you are viewing a single comment's thread
view the rest of the comments
[–] technohacker@programming.dev 7 points 3 months ago* (last edited 3 months ago)

They stand for Floating Point 16-bit, 8-bit and 4 bit respectively. Normal floating point numbers are generally 32 or 64 bits in size, so if you're willing to sacrifice some range, you can save a lot of space used by the model. Oh, and it's about the model rather than the GPU