


























Abstract:Large language models (LLMs) impose rapidly growing energy demands, creating an emerging energy and carbon crisis driven by large-scale inference. Solar-powered, AI-enabled low Earth orbit (LEO) satellites have been proposed to mitigate terrestrial electricity consumption, but their lifecycle carbon footprint remains poorly understood due to launch emissions, satellite manufacturing, and radiation-hardened hardware requirements. This paper presents \textit{LLMSpace}, the first carbon modeling framework for LLM inference on AI-enabled LEO satellites. LLMSpace jointly models operational and embodied carbon, peripheral subsystems, radiation-hardened accelerators and memories, and LLM-specific workload characteristics such as prefill-decode behavior and token generation. Using realistic satellite and GPU configurations, LLMSpace reveals key trade-offs among carbon footprint, inference latency, hardware design, and operational lifetime for sustainable space-based LLM inference. Source code: this https URL.
| Comments: | 12 pages, 4 figures, 6 tables |
| Subjects: | Machine Learning (cs.LG); Computers and Society (cs.CY) |
| Cite as: | arXiv:2605.05615 [cs.LG] |
| (or arXiv:2605.05615v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.05615 arXiv-issued DOI via DataCite (pending registration) |
From: Lei Jiang [view email]
[v1]
Thu, 7 May 2026 03:06:56 UTC (392 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。