# Post-Training Quantization via Residual Truncation and Zero Suppression for Diffusion Models Source: [Post-Training Quantization via Residual Truncation and Zero Suppression for Diffusion Models]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:48:24.291Z Authors: Donghoon Kim, Dongyoung Lee, Ik Joon Chang, Sung-Ho Bae Published: 2025-09-30T15:55:42.000Z ## Abstract Diffusion models achieve high-quality image generation but face deployment challenges due to their high computational requirements. Although 8-bit outlier-aware post-training quantization (PTQ) matches full-precision performance, extending PTQ to 4 bits remains challenging. Larger step sizes in 4-bit quantization amplify rounding errors in dense, low-magnitude activations, leading to the loss of fine-grained textures. We hypothesize that not only outliers but also small activations are critical for texture fidelity. To this end, we propose Quantization via Residual Truncation and Zero Suppression (QuaRTZ), a 4-bit PTQ scheme for diffusion models. QuaRTZ applies 8-bit min-max quantization for outlier handling and compresses to 4 bits via leading-zero suppression to retain LSBs, thereby preserving texture details. Our approach reduces rounding errors and improves quantization efficiency by balancing outlier preservation and LSB precision. Both theoretical derivations and empirical evaluations demonstrate the generalizability of QuaRTZ across diverse activation distributions. Notably, 4-bit QuaRTZ achieves an FID of 6.98 on FLUX.1-schnell, outperforming SVDQuant that requires auxiliary FP16 branches. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Camouflaged Object Detection on CAMO (test) (S\_alpha, F\_w\_beta, E\_m, F\_m\_beta, MAE)](): Camouflaged Object Detection; CAMO (test); S\_alpha: 41.6. - [Camouflaged Object Detection on NC4K (S\_alpha, F\_m\_beta, MAE)](): Camouflaged Object Detection; NC4K; S\_alpha: 44.1. - [Camouflaged Object Detection on CHAMELEON](): Camouflaged Object Detection; Chameleon; S-measure (S\_alpha): 44.7. - [Camouflaged Object Detection on COD10K (test)](): Camouflaged Object Detection; COD10K (test); S-measure (S\_alpha): 0.471. ## Original sources and implementation [Original paper]() [PDF]()