# 6Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models Source: [6Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models]() Collection index: [llms.txt]() Data updated: 2026-03-29T06:00:01.233Z Authors: Rundong Su, Jintao Zhang, Zhihang Yuan, Haojie Duanmu, Jianfei Chen, Jun Zhu Published: 2026-03-19T10:45:11.000Z ## Abstract Diffusion transformers have demonstrated remarkable capabilities in generating videos. However, their practical deployment is severely constrained by high memory usage and computational cost. Post-Training Quantization provides a practical way to reduce memory usage and boost computation speed. Existing quantization methods typically apply a static bit-width allocation, overlooking the quantization difficulty of activations across diffusion timesteps, leading to a suboptimal trade-off between efficiency and quality. In this paper, we propose a inference time NVFP4/INT8 Mixed-Precision Quantization framework. We find a strong linear correlation between a block's input-output difference and the quantization sensitivity of its internal linear layers. Based on this insight, we design a lightweight predictor that dynamically allocates NVFP4 to temporally stable layers to maximize memory compression, while selectively preserving INT8 for volatile layers to ensure robustness. This adaptive precision strategy enables aggressive quantization without compromising generation quality. Beside this, we observe that the residual between the input and output of a Transformer block exhibits high temporal consistency across timesteps. Leveraging this temporal redundancy, we introduce Temporal Delta Cache (TDC) to skip computations for these invariant blocks, further reducing the computational cost. Extensive experiments demonstrate that our method achieves 1.92$\\times$ end-to-end acceleration and 3.32$\\times$ memory reduction, setting a new baseline for efficient inference in Video DiTs. ## 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. - [Video Generation on VBench (8 Perceptual Metrics Subset)](): Video Generation; VBench; Aesthetic Quality: 57.24. ## Original sources and implementation [Original paper]() [PDF]()