EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Sustainability via Large Language Model Right-Sizing

Jennifer Haase, Finn Klessascheck, Jan Mendling, Sebastian Pokutta

IEEE Transactions on Sustainable Computing · 2026-07 · 11 (4) · 426-438

DOI: 10.1109/tsusc.2026.3697261 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Sustainable Computing, 2026-07. Verfasst von Jennifer Haase und 3 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Federal Ministry of Research, Deutsche Forschungsgemeinschaft, SFB 1404/2.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) are increasingly embedded in organizational workflows, raising concerns about energy use, costs, and data sovereignty. While benchmarks often celebrate cutting-edge models, real-world deployment requires a broader question: when is a smaller, locally deployable model “good enough”? This study evaluates eleven proprietary and open-weight LLMs on ten everyday occupational tasks, including summarizing, scheduling, and drafting emails and proposals. Using a dual-LLM evaluation framework, we automated task execution and standardized assessment across ten criteria of quality, accuracy, and ethical responsibility. Results show GPT-4o delivers top performance but with significantly higher costs and environmental impact. Smaller models such as Gemma-3 and Phi-4 performed strongly on most tasks, supporting their viability where cost-efficiency, local use, or privacy matter. A cluster analysis identified three groups—High, Balanced, and Baseline Performance Models—highlighting trade-offs between quality, control, and sustainability. Task type shaped effectiveness: conceptual tasks were most challenging, while aggregation and transformation tasks yielded better outcomes. We argue for shifting from performance-maximizing benchmarks to task- and context-aware sufficiency assessments that reflect organizational priorities. Our approach offers a replicable method to evaluate AI models from a sustainability perspective and provides practical recommendations for responsible LLM deployment.

Förderung

  • Federal Ministry of Research
  • Deutsche Forschungsgemeinschaft
  • SFB 1404/2
  • DFG Cluster of Excellence MATH
  • Zuse Institute Berlin via the RISE@ZIB services hosting

Zitieren

APA

Haase, J., Klessascheck, F., Mendling, J., & Pokutta, S. (2026). Sustainability via Large Language Model Right-Sizing. IEEE Transactions on Sustainable Computing, 11(4), 426-438. https://doi.org/10.1109/tsusc.2026.3697261

Vancouver

Haase J, Klessascheck F, Mendling J, Pokutta S. Sustainability via Large Language Model Right-Sizing. IEEE Transactions on Sustainable Computing. 2026;11(4):426-438. doi:10.1109/tsusc.2026.3697261

BibTeX
@article{Haase2026,
  author = {Haase, Jennifer and Klessascheck, Finn and Mendling, Jan and Pokutta, Sebastian},
  title = {Sustainability via Large Language Model Right-Sizing},
  journal = {IEEE Transactions on Sustainable Computing},
  year = {2026},
  volume = {11},
  number = {4},
  pages = {426--438},
  doi = {10.1109/tsusc.2026.3697261}
}
Kostenlos starten →