Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.15734 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915455752470528 |
|---|---|
| author | Elsworth, Cooper Huang, Keguo Patterson, David Schneider, Ian Sedivy, Robert Goodman, Savannah Townsend, Ben Ranganathan, Parthasarathy Dean, Jeff Vahdat, Amin Gomes, Ben Manyika, James |
| author_facet | Elsworth, Cooper Huang, Keguo Patterson, David Schneider, Ian Sedivy, Robert Goodman, Savannah Townsend, Ben Ranganathan, Parthasarathy Dean, Jeff Vahdat, Amin Gomes, Ben Manyika, James |
| contents | The transformative power of AI is undeniable - but as user adoption accelerates, so does the need to understand and mitigate the environmental impact of AI serving. However, no studies have measured AI serving environmental metrics in a production environment. This paper addresses this gap by proposing and executing a comprehensive methodology for measuring the energy usage, carbon emissions, and water consumption of AI inference workloads in a large-scale, AI production environment. Our approach accounts for the full stack of AI serving infrastructure - including active AI accelerator power, host system energy, idle machine capacity, and data center energy overhead. Through detailed instrumentation of Google's AI infrastructure for serving the Gemini AI assistant, we find the median Gemini Apps text prompt consumes 0.24 Wh of energy - a figure substantially lower than many public estimates. We also show that Google's software efficiency efforts and clean energy procurement have driven a 33x reduction in energy consumption and a 44x reduction in carbon footprint for the median Gemini Apps text prompt over one year. We identify that the median Gemini Apps text prompt uses less energy than watching nine seconds of television (0.24 Wh) and consumes the equivalent of five drops of water (0.26 mL). While these impacts are low compared to other daily activities, reducing the environmental impact of AI serving continues to warrant important attention. Towards this objective, we propose that a comprehensive measurement of AI serving environmental metrics is critical for accurately comparing models, and to properly incentivize efficiency gains across the full AI serving stack. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15734 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Measuring the environmental impact of delivering AI at Google Scale Elsworth, Cooper Huang, Keguo Patterson, David Schneider, Ian Sedivy, Robert Goodman, Savannah Townsend, Ben Ranganathan, Parthasarathy Dean, Jeff Vahdat, Amin Gomes, Ben Manyika, James Artificial Intelligence The transformative power of AI is undeniable - but as user adoption accelerates, so does the need to understand and mitigate the environmental impact of AI serving. However, no studies have measured AI serving environmental metrics in a production environment. This paper addresses this gap by proposing and executing a comprehensive methodology for measuring the energy usage, carbon emissions, and water consumption of AI inference workloads in a large-scale, AI production environment. Our approach accounts for the full stack of AI serving infrastructure - including active AI accelerator power, host system energy, idle machine capacity, and data center energy overhead. Through detailed instrumentation of Google's AI infrastructure for serving the Gemini AI assistant, we find the median Gemini Apps text prompt consumes 0.24 Wh of energy - a figure substantially lower than many public estimates. We also show that Google's software efficiency efforts and clean energy procurement have driven a 33x reduction in energy consumption and a 44x reduction in carbon footprint for the median Gemini Apps text prompt over one year. We identify that the median Gemini Apps text prompt uses less energy than watching nine seconds of television (0.24 Wh) and consumes the equivalent of five drops of water (0.26 mL). While these impacts are low compared to other daily activities, reducing the environmental impact of AI serving continues to warrant important attention. Towards this objective, we propose that a comprehensive measurement of AI serving environmental metrics is critical for accurately comparing models, and to properly incentivize efficiency gains across the full AI serving stack. |
| title | Measuring the environmental impact of delivering AI at Google Scale |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.15734 |