Slacker News Slacker News logo featuring a lazy sloth with a folded newspaper hat
  • top
  • new
  • show
  • ask
  • jobs
Library
← Back to context

Comment by vlovich123

3 months ago

Quantization by definition lower memory requirements - instead of using f16 for weights, you are using q8, q6, q4, or q2 which means the weights are smaller by 2x, ~2.7x, 4x or 8x respectively.

That doesn’t necessarily translate to the full memory reduction because of interim compute tensors and KV cache, but those can also be quantized.

0 comments

vlovich123

Reply

No comments yet

Contribute on Hacker News ↗

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities