Energy costs of communicating with AI
This study presents a comprehensive evaluation of the environmental cost of large language models (LLMs) by analyzing their performance, token usage, and CO2 equivalent emissions across 14 LLMs ranging from 7 to 72 billion parameters. Each LLM was tasked with answering 500 multiple-choice and 500 fr...
Saved in:
| Main Authors: | Maximilian Dauner, Gudrun Socher |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-06-01
|
| Series: | Frontiers in Communication |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcomm.2025.1572947/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Integrated Energy and Environmental Modeling to Design Cost-Effective Building Solutions at a Regional Level
by: Mariana Januário, et al.
Published: (2024-11-01) -
A little more conversation, a little more action, please: the carbon footprint of travelling to conferences of the European Health Psychology Society
by: Lisa M. Warner, et al.
Published: (2025-12-01) -
Bridging neuroscience and AI: a survey on large language models for neurological signal interpretation
by: Sreejith Chandrasekharan, et al.
Published: (2025-06-01) -
Impact of Green bond on renewable energy transition
by: Luu Hanh Nguyen, et al.
Published: (2024-10-01) -
Optimal sizing, techno-economic, and environmental assessment of hybrid renewable energy systems
by: Mohammad Reza Gharib, et al.
Published: (2025-05-01)