The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inference
For NLP practitioners and deployers of multilingual LLMs, this reveals a systemic energy inequity that should be considered alongside performance metrics.
This paper quantifies energy consumption disparities in multilingual LLM inference, finding up to 8.3x variation per token and 179x total energy difference between languages (English: 17.6 kJ vs. Pashto: 3,147 kJ), with high-energy languages also showing lower task accuracy.
Large language models (LLMs) are increasingly deployed in multilingual settings, yet the energy costs of serving these models across different languages remain poorly understood. We present a systematic study of inference energy consumption across languages with ML.Energy framework (Chung et al., 2026). We find striking disparities: energy consumption per output token varies by up to 8.3 times across languages, while total energy for a fixed set of requests varies by up to 179 times between the cheapest (English, 17.6 kJ) and the most expensive (Pashto, 3,147 kJ) languages. Our analysis shows that this disparity is driven by two compounding factors: (1) higher per-token energy costs for languages using complex or rare scripts, and (2) more tokens generated for low-resource languages. Moreover, we find a double cost + performance penalty: languages with the highest energy footprints also tend to achieve the lowest task accuracy. We reveal that the energy divide persists across models, hardware, and tasks, suggesting a systemic energy inequity in multilingual LLM deployment. Finally, we recommend that the community treat energy as a first-class evaluation axis, extend reporting checklists and model cards to include it, and adopt deployment-side mitigations for better energy efficiency.