Vibeleaderboard
← All Intel
Intel / article

Scalar codebook quantization, an interactive guide

Source
myli.page
Author
tslmy
Date
Why it matters

Explains how weights get to 4 bits and why each refinement (per-group scales, rotation, one shared codebook) fixes a specific failure, useful for anyone choosing or building local models.

Terms in this piece · Glossary
  • quantization — Shrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.
Recommended reads
Comments

Checking sign-in…

Loading comments…