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

arXiv:2608.00008v1 Announce Type: new Abstract: 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 nine open-source LLMs (1B 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/token), and throughput (tok/s). Our findings suggest that factors beyond raw parameter count, including model architecture and quantization strategy, drive energy efficiency. Specifically, gemma3:1b and llama3.2:1b achieve the lowest energy cost (0.56 J/token and 0.65 J/token) and the highest throughput (>170 tok/s). In contrast, the 7B-Mistral model consumes up to 4.4x more energy per token than the most efficient model. Notably, qwen3.5:2b exhibits anomalously high per-prompt energy due to extended internal reasoning, highlighting the need to distinguish between token generation modes in efficiency metrics.

Abstract: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 nine open-source LLMs (1B 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/token), and throughput (tok/s). Our findings suggest that factors beyond raw parameter count, including model architecture and quantization strategy, drive energy efficiency. Specifically, gemma3:1b and llama3.2:1b achieve the lowest energy cost (0.56 J/token and 0.65 J/token) and the highest throughput (>170 tok/s). In contrast, the 7B-Mistral model consumes up to 4.4x more energy per token than the most efficient model. Notably, qwen3.5:2b exhibits anomalously high per-prompt energy due to extended internal reasoning, highlighting the need to distinguish between token generation modes in efficiency metrics.

Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET); Performance (cs.PF)

arXiv:2608.00008 [cs.AI]

(or arXiv:2608.00008v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2608.00008 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

analiza aiqbench

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

Subiecte conexe