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 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.
Abstract (translated)
URL
https://arxiv.org/abs/2608.00008
