Air-LLM: Broadcasting AI Weights for Edge LLM Inference via RF Computing

A paper submitted to arXiv on 30 September 2026 presents AIR-LLM, an edge inference architecture in which a central radio such as a 5G base station broadcasts LLM weights over the air so edge devices compute the general matrix-vector multiplication of inference directly in the RF domain using RF mixers, without storing or loading weights. Tested on NVIDIA Sionna ray-traced channels of two real-world urban scenes with profiling of a real RF mixer, AIR-LLM degraded WikiText-2 perplexity by 4.0% on LLaMA-3.1-8B while saving 157.7x and 40.4x energy versus FP16 and weight-only quantization baselines, and with 20 users cut airtime 104.1x and 26.0x shorter, respectively. Because the central radio stays user-unaware, one broadcast serves unlimited users within coverage.

Computer Science Information Theory Submitted on 30 Sep 2026 Title:AIR-LLM: Broadcasting AI Weights over Radio for Memory-Free Edge LLM Inference via RF Computing View PDF https://arxiv.org/pdf/2610.00465 HTML experimental https://arxiv.org/html/2610.00465v1 Abstract:Next-generation large language models LLMs are expanding from the cloud to ubiquitous edge devices. However, edge devices typically either lack the memory to store increasingly large LLM weights or, even with enough memory, spend unaffordable energy on loading the weights. This raises our question: can an edge device run an LLM without storing or loading its weights, but receive them over the air and consume them on the fly? Inspired by wireless broadcasting, we present AIR-LLM, an LLM inference architecture for edge devices, which is composed of: i a central radio e.g., 5G base stations that broadcasts the LLM weights into the air, and ii the edge user that receives the weights and completes the general matrix-vector multiplication GEMV of LLM inference directly in the radio frequency RF domain using RF mixers. To further shorten the airtime, AIR-LLM exploits MIMO spatial multiplexing and proposes an energy-efficient precoder-postcoder pair on the edge to calibrate its own wireless channel. Since the central radio stays user-unaware, AIR-LLM is user-scalable so that one broadcast serves unlimited users within its coverage. We implement AIR-LLM on the NVIDIA Sionna ray-traced channels of two real-world urban scenes and the profiling of a real RF mixer. With a WikiText-2 perplexity degradation of 4.0% on LLaMA-3.1-8B, AIR-LLM saves the energy by 157.7x/40.4x against the FP16 and weight-only quantization baselines; with 20 users, its airtime is 104.1x/26.0x shorter, respectively. Current browse context: cs.IT References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .