# LiteVLA-Edge: Quantized On-Device Multimodal Control for Embedded Robotics

arXiv: https://arxiv.org/abs/2603.03380 · HTML: https://mlsanity.com/paper/2603.03380/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models.
- Builds on 9 of its 9 references that are in the map.
- First posted on arXiv 3 Mar 2026.

## Placed in

- Vision-language-action models / [Efficient VLA inference and adaptation](https://mlsanity.com/vla/efficient-vla-inference-and-adaptation/)

## Builds on (most cited first, 9 of 9)

- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025)
- [PaliGemma 2: A Family of Versatile VLMs for Transfer](https://mlsanity.com/paper/2412.03555/) (2024)
- [TinyLLaVA: A Framework of Small-scale Large Multimodal Models](https://mlsanity.com/paper/2402.14289/) (2024)
- [EdgeVLA: Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2507.14049/) (2025)
- [Lite VLA: Efficient Vision-Language-Action Control on CPU-Bound Edge Robots](https://mlsanity.com/paper/2511.05642/) (2025)

## Built on by (most cited first, 4 of 4)

- [vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models](https://mlsanity.com/paper/2606.08094/) (2026)
- [LiteVLA-H: Dual-Rate Vision-Language-Action Inference for Onboard Aerial Guidance and Semantic Perception](https://mlsanity.com/paper/2605.00884/) (2026)
- [When Faster VLA Deployment Changes Closed-Loop Behavior: Task Success-Latency Analysis of SmolVLA Across PyTorch and ONNX Variants](https://mlsanity.com/paper/2609.14146/) (2026)
- [EdgeVLN: Runtime-Aware Deployment Ready Quantized Vision Language Navigation Model](https://mlsanity.com/paper/2609.35570/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models provide a unified framework for perception, language conditioning, and action generation, but many existing systems remain difficult to deploy in embedded robotic settings because of their computational requirements and inference latency. In this paper, we present LiteVLA-Edge, a deployment-oriented VLA pipeline for fully on-device inference on Jetson Orin-class hardware. Our approach combines supervised image-to-action fine-tuning in FP32 with post-training 4-bit GGUF quantization and GPU-accelerated inference through the textttllama.cpp runtime. Under our deployment configuration, LiteVLA-Edge achieves a mean end-to-end latency of 150.5,ms (approximately 6.6,Hz) while operating entirely offline within a ROS~2-integrated perception--reasoning--action pipeline. Rather than introducing a new policy objective, our contribution is a practical systems path for executing compact multimodal control models locally on embedded hardware while preserving modular interfaces between perception, reasoning, and actuation. These results establish timing feasibility for reactive language-conditioned control and provide a reproducible baseline for future task-level evaluation of on-device VLAs in robotics.