Skip to content
gentic.news — AI News Intelligence Platform

Technique · inference

AWQ (Activation-Aware Weight Quantization)

4-bit weight quantization that preserves salient weights based on activation magnitudes, matching GPTQ quality with faster inference.

Origin: MIT, 2023-06Read origin paper →Also known as: AWQ
0
Products deploying
Avg research → prod
First commercial deploy

Deployment timeline

No verified deployments yet in our tracked product set.