# Seeing at the Edge: Energy Characterization of Vision-Language Model Inference on Edge Platforms

arXiv: https://arxiv.org/abs/2610.20136 · HTML: https://mlsanity.com/paper/2610.20136/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Placed in

- Multimodal LLMs / vision-language models

## Builds on (most cited first, 16 of 16)

- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [MLPerf Inference Benchmark](https://mlsanity.com/paper/1911.02549/) (2019)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [Mobile Edge Intelligence for Large Language Models: A Contemporary Survey](https://mlsanity.com/paper/2407.18921/) (2024)
- [MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices](https://mlsanity.com/paper/2312.16886/) (2023)
- [Small Language Models: Survey, Measurements, and Insights](https://mlsanity.com/paper/2409.15790/) (2024)
- [T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge](https://mlsanity.com/paper/2407.00088/) (2024)
- [MELTing point: Mobile Evaluation of Language Transformers](https://mlsanity.com/paper/2403.12844/) (2024)
- [Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency](https://mlsanity.com/paper/2504.03360/) (2025)
- [The Price of Prompting: Profiling Energy Use in Large Language Models Inference](https://mlsanity.com/paper/2407.16893/) (2024)
- [MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases](https://mlsanity.com/paper/2406.10290/) (2024)
- [PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms](https://mlsanity.com/paper/2410.05315/) (2024)
- [LLM Inference at the Edge: Mobile, NPU, and GPU Performance Efficiency Trade-offs Under Sustained Load](https://mlsanity.com/paper/2603.23640/) (2026)
- [Accurate Calibration of Power Measurements from Internal Power Sensors on NVIDIA Jetson Devices](https://mlsanity.com/paper/2306.13107/) (2023)
- [Seeing is Free, Speaking is Not: Uncovering the True Energy Bottleneck in Edge VLM Inference](https://mlsanity.com/paper/2607.09520/) (2026)

## Abstract (arXiv)

Vision-language models (VLMs) are moving onto edge devices, but little is known about how much energy they draw on single-board computers with NPU or GPU accelerators, or where that energy goes. We measure total-system energy, latency, and thermal behavior of Qwen2-VL-2B-Instruct and its text-only sibling on a Raspberry Pi 5 with a Hailo-10H NPU and on a Jetson Orin Nano Super, on both CPU and accelerator, and separate the fixed energy of each request from the energy that grows with output length. Because the accelerators use different quantization and serving software, we compare deployment stacks rather than silicon. Three findings stand out. First, NPU offloading makes the Pi a much more efficient VLM platform: it cuts energy per generated token by about two-thirds, leaves the host CPU largely free, and avoids the thermal throttling that the CPU backend reaches in sustained use. Second, an image adds both fixed and per-token energy, but at typical response lengths generating the answer costs far more than processing the image. Third, the Jetson GPU favors short responses through its lower fixed cost per request, whereas the Pi NPU favors longer ones through its lower cost per output token; their energy curves cross near 40 output tokens.