BLAST RADIUS

Open-weight & owned stack · Quantization efficiency

ButterflyQuant Targets Ultra-Low-Bit LLM Deployment

Sep 11, 2026

ButterflyQuant used learnable orthogonal butterfly transforms to reduce memory requirements for ultra-low-bit LLM deployment.

Read the original at lacuna.tiptreesystems.comOpens the publisher's site in a new tab

More in Open-weight & owned stack