BLAST RADIUS

Open-weight & owned stack · Quantization efficiency

PolarQuant Proposes Near-Lossless LLM Weight Compression

Sep 13, 2026

PolarQuant proposed Hadamard-rotation post-training quantization to compress LLM weights while preserving performance under Gaussian weight assumptions.

Read the original at awesomepapers.ioOpens the publisher's site in a new tab

More in Open-weight & owned stack