Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency

Deploying Large Language Models (LLMs) on edge devices presents significant challenges due to computational constraints, memory limitations, inference speed, and energy consumption. Model quantization has emerged as a key technique to enable efficient LLM inference by reducing model size and computational overhead. In this study, we conduct a comprehensive analysis of 28 quantized LLMs from the Ollama library, which applies by default Post-Training Quantization (PTQ) and weight-only quantization techniques, deployed on an edge device (Raspberry Pi 4 with 4GB RAM). We evaluate energy efficiency, inference performance, and output accuracy across multiple quantization levels and task types. Models are benchmarked on five standardized datasets (CommonsenseQA, BIG-Bench Hard, TruthfulQA, GSM8K, and HumanEval), and we employ a high-resolution, hardware-based energy measurement tool to capture real-world power consumption. Our findings reveal the trade-offs between energy efficiency, inference speed, and accuracy in different quantization settings, highlighting configurations that optimize LLM deployment for resource-constrained environments. By integrating hardware-level energy profiling with LLM benchmarking, this study provides actionable insights for sustainable AI, bridging a critical gap in existing research on energy-aware LLM deployment.

@article{husom2025_2504.03360,
  title={ Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency },
  author={ Erik Johannes Husom and Arda Goknil and Merve Astekin and Lwin Khin Shar and Andre Kåsen and Sagar Sen and Benedikt Andreas Mithassel and Ahmet Soylu },
  journal={arXiv preprint arXiv:2504.03360},
  year={ 2025 }
}