cd /news/large-language-models/how-do-prompt-variations-affect-ener… · home topics large-language-models article
[ARTICLE · art-119801] src=arxiv.org ↗ pub= topic=large-language-models verified=true sentiment=· neutral

How Do Prompt Variations Affect Energy Consumption in On-Device LLMs?

A new arXiv study (2609.01798v1) finds that prompt design significantly affects energy consumption in on-device large language models (LLMs), with cognitive load primarily impacting energy cost per token and phrasing pattern affecting energy through token usage. The empirical study, covering multiple prompt properties, datasets, models, and devices, shows that prompt design reshapes the attainable energy-quality frontier differently across models, underscoring the need for model-aware prompt design in energy-efficient on-device LLM inference.

read1 min views9 publishedSep 3, 2026

arXiv:2609.01798v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed on mobile devices, making energy efficiency a key deployment constraint, yet the energy impact of prompt design remains underexplored. This paper aims to understand how two prompt properties, cognitive load and phrasing pattern, shape the energy behavior of on-device LLM inference. We conduct a broad empirical study covering prompt properties, datasets, models, and devices, with phase-level profiling that separates prefill and decode energy. We find that cognitive load primarily affects the energy cost per token, while phrasing pattern affects energy largely through token usage. Our energy-quality analysis further shows that prompt design reshapes the attainable frontier differently across models, highlighting the need for model-aware prompt design in energy-efficient on-device LLM inference. Code, datasets, and scripts are available at https://amai-gsu.github.io/PromptProperty/.

── more in #large-language-models 4 stories · sorted by recency
── more on @arxiv 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/how-do-prompt-variat…] indexed:0 read:1min 2026-09-03 ·