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

arXiv: https://arxiv.org/abs/2608.00008 · HTML: https://mlsanity.com/paper/2608.00008/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 12 Jun 2026.

## Builds on (most cited first, 8 of 8)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [Characterizing LLM Inference Energy-Performance Tradeoffs across Workloads and GPU Scaling](https://mlsanity.com/paper/2501.08219/) (2025)
- [Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models](https://mlsanity.com/paper/2502.05610/) (2025)

## Abstract (arXiv)

The local deployment of large language models (LLMs) is gaining traction due to privacy concerns and the desire for on-premise inference. However, the energy costs on consumer hardware remain poorly characterized, as most benchmarks focus solely on accuracy. This paper presents a reproducible, hardware-level energy benchmark of 18 open-source LLMs (0.5B to 7B parameters) executed on a single consumer GPU (RTX 4060ti 16GB). Using the Ollama inference engine, GPU power draw was sampled at 2hz via nvidia-smi across a fixed prompt set. We evaluate mean/peak power, total energy per prompt (J/prompt), energy per output token (J/tok), and throughput (tok/s). Our findings suggest that factors beyond raw parameter count, including model architecture and quantization strategy, drive energy efficiency. Specifically, qwen2.5:0.5b and tinyllama:1.1b achieve the lowest energy cost (0.2747 J/tok and 0.3234 J/tok) and the highest throughput (>325 tok/s). In contrast, the 7B-Mistral model consumes up to 8.6x more energy per token than the most efficient model. Notably, qwen3.5:0.8b(on) exhibits anomalously high per-prompt energy due to extended internal reasoning, highlighting the need to distinguish between token generation modes in efficiency metrics.