# VLA-HWBench: Where inference time goes for VLA models on edge hardware

- Source: arXiv cs.RO
- Published: 2026-10-27T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/y5uwmzn9218hqisnqwi3hdgrj
- Original: https://arxiv.org/abs/2610.34717

## Summary

VLA-HWBench breaks down inference into seven stages for 18 open-source VLA models on NVIDIA Jetson AGX Thor and AMD Ryzen AI Max+ PRO 395, finding that action-generation strategy determines latency more than model size does, with parameter count explaining at most 15% of latency variance.