ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models

Researchers introduced ActQuant, a sub-4-bit quantization framework for Vision-Language-Action (VLA) models that reduces computational demands for edge deployment. The method achieved 95% performance retention at 3 bits-per-weight on the LIBERO benchmark and compressed the OpenVLA-OFT backbone from 14.3 GB to 2.7 GB (5.3x) at 2.5 bits-per-weight. On a physical UR3 robotic arm, ActQuant maintained baseline success rates while reducing memory footprint by 2.5x.

arXiv:2605.24011v1 Announce Type: new Abstract: Vision-Language-Action VLA models exhibit remarkable action generation for embodied intelligence, but their heavy compute make deployment on edge platforms impractical. Aggressive, sub-4-bit weight quantization is the natural solution, yet existing post-training quantization PTQ methods suffer severe performance degradation in this regime. To address this, we introduce ActQuant, an action-guided mixed-precision PTQ framework that operates in two stages: 1 an inter-tensor bit allocator that assigns each weight matrix a single bit-width based on how much it contributes to predicting the agent's actions; 2 an intra-tensor scale optimizer tunes per-block quantization scales using action-aware curvature, so that dynamic range is concentrated on the weights most influential for control. To deliver the on-device benefits of our aggressive quantization, we further introduce OmniModel.cpp, an agentic conversion pipeline that ports architectures into a native C/C++ runtime with efficient low-bit kernels. We evaluate ActQuant both in simulation and on a real-world 6-DoF UR3 arm, with all models deployed through OmniModel.cpp. On the LIBERO benchmark, ActQuant is the only method that operates at or below 3 bits-per-weight, retaining 95.0% on OpenVLA-OFT and 94.8% on $\pi {0.5}$. Pushed further, ActQuant reaches 2.5 bpw at 90.1% on OpenVLA-OFT, compressing the backbone from 14.3 GB to 2.7 GB 5.3$\times$ . On the physical UR3 arm, $\pi {0.5}$ quantized with ActQuant retains the baseline's success rate while reducing the memory footprint by 2.5$\times$.