trends.barnas.net

method · first seen 31 Oct 2026

4-bit weight quantization

Also: INT4

Compressing neural network weights to 4-bit precision to reduce memory and speed up inference.

Mentions per week

0119 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

mixture of expertsmicroscaling floating-point quantization