inference/research
verifiedhigh · 0.88updated 2026-10-03

Extreme Compression of Large Language Models via Additive Quantization / AQLM (Egiazarian et al.)

paper

Fields

id
sources/qlab-aqlm-paper
URL
https://arxiv.org/abs/2401.06118
Publisher
arXiv
Kind
paper
Published
2024-01-11
Accessed
2026-10-03
notes
v4. Multi-codebook additive quantization; 2-bit and 3-bit Pareto claims.

Notes

v4. Multi-codebook additive quantization; 2-bit and 3-bit Pareto claims.

Cross-references

This record references no other records.