Energy Efficiency of Locally Deployed LLMs: A Preliminary Quantitative GPU Power Benchmark on Consumer Hardware

arXiv:2608.00008 · cs.AI, cs.ET, cs.PF · Submitted 2026-06-12 · Read on arXiv

cs.AI, cs.ET, cs.PF

Submitted: 2026-06-12

Updated: 2026-09-25

Code: https://github.com/fhac-ida/GreenCode-LLM-Benchmark

Terminology

• Benchmark — 19× in this paper · explained in 2 episodes
• Quantization — 12× in this paper · explained in 12 episodes
• Energy Efficiency — 11× in this paper · explained in 3 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Benchmarking — 4× in this paper · explained in 4 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Decode — 2× in this paper · explained in 2 episodes
• Active Inference — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes

Sources

• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
• Characterizing LLM Inference Energy-Performance Tradeoffs across Workloads and GPU Scaling
• Qwen3 Technical Report

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection