# Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite

arXiv: https://arxiv.org/abs/2606.11257 · HTML: https://mlsanity.com/paper/2606.11257/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 32 of its 52 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 30 of 32)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [EmbeddingGemma: Powerful and Lightweight Text Representations](https://mlsanity.com/paper/2509.20354/) (2025)
- [On-Device Language Models: A Comprehensive Review](https://mlsanity.com/paper/2409.00088/) (2024)
- [Fast On-device LLM Inference with NPUs](https://mlsanity.com/paper/2407.05858/) (2024)
- [FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval](https://mlsanity.com/paper/2503.21309/) (2025)
- [DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models](https://mlsanity.com/paper/2505.13975/) (2025)
- [Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysis](https://mlsanity.com/paper/2603.16877/) (2026)
- [When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems](https://mlsanity.com/paper/2606.00448/) (2026)
- [Learning How to Use Tools, Not Just When: Pattern-Aware Tool-Integrated Reasoning](https://mlsanity.com/paper/2509.23292/) (2025)
- [Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation](https://mlsanity.com/paper/2510.10925/) (2025)
- [Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models](https://mlsanity.com/paper/2603.21389/) (2026)
- [Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict](https://mlsanity.com/paper/2605.14473/) (2026)
- [Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG](https://mlsanity.com/paper/2605.28044/) (2026)
- [Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off](https://mlsanity.com/paper/2603.26815/) (2026)
- [Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection](https://mlsanity.com/paper/2605.24834/) (2026)
- [FinSentLLM: Multi-LLM and Structured Semantic Signals for Enhanced Financial Sentiment Forecasting](https://mlsanity.com/paper/2509.12638/) (2025)
- [CATCH: A Modular Cross-domain Adaptive Template with Hook](https://mlsanity.com/paper/2510.26582/) (2025)
- [Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.06842/) (2026)
- [Coverage-Aware Web Crawling for Domain-Specific Supplier Discovery via a Web--Knowledge--Web Pipeline](https://mlsanity.com/paper/2602.24262/) (2026)
- [VisualLeakBench: Auditing the Fragility of Large Vision-Language Models against PII Leakage and Social Engineering](https://mlsanity.com/paper/2603.13385/) (2026)
- [Architecture Matters More Than Scale: A Comparative Study of Retrieval and Memory Augmentation for Financial QA Under SME Compute Constraints](https://mlsanity.com/paper/2604.17979/) (2026)
- [FAST: A Synergistic Framework of Attention and State-space Models for Spatiotemporal Traffic Prediction](https://mlsanity.com/paper/2604.13453/) (2026)

## Built on by (most cited first, 1 of 1)

- [When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost](https://mlsanity.com/paper/2607.24010/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) pipelines are compute-intensive, combining embedding, retrieval, reranking, and large language model (LLM) generation. Running them entirely on-device benefits privacy, latency, and offline use, but the energy cost of CPU inference is a major barrier. We present what is, to our knowledge, the first end-to-end RAG pipeline that runs all neural stages -- embedding, reranking, and LLM generation -- on the Qualcomm Hexagon NPU of the Snapdragon X Elite. Profiling on a Dell XPS 13 laptop, we compare NPU-accelerated RAG against CPU and OpenCL/Adreno GPU baselines on indexing and query workloads. On indexing, the NPU achieves 9.1x higher embedding throughput and 12.3x less system energy. On a 120-query Wikipedia-passage benchmark, it delivers 18.1x faster LLM prefilling, 4.0x lower end-to-end query latency, and 4.0x less system energy than the CPU baseline; the same workload on the integrated GPU is 1.7x slower than CPU and uses 6.5x more energy than the NPU. A GPT-4.1 LLM-as-judge evaluation finds NPU answer quality on par with CPU and GPU within evaluator noise (mean 9.32 vs. 8.95 vs. 9.03 on a 1-10 rubric), with 86.7% of queries scoring identically across all three backends. On the Snapdragon X Elite / Hexagon class of laptop SoC, the NPU thus enables practical, energy-efficient on-device RAG without quality regression -- a sustainable path toward green edge intelligence that we expect to generalize to comparable mobile NPUs (Apple Neural Engine, Intel NPU, MediaTek APU) as their software stacks mature.