Edge AI Optimization: Techniques for Shrinking Large Language Models (LLMs) to Run Efficiently on Mobile Hardware
International Journal of Advanced Research in Science Communication and Technology · 24.06.2026 · 267
DOI: 10.48175/ijarsct-37136 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Advanced Research in Science Communication and Technology, online erschienen am 24.06.2026. Verfasst von Vaishnavi Siddhtekakar and Prof. Sandeep Vishwakarma. Die Arbeit nennt 14 Literaturangaben.
Abstract (Originalsprache)
Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, generation, and reasoning. However, their deployment on mobile and edge devices remains challenging due to constraints in memory, computational power, energy consumption, and storage. Edge AI optimization focuses on reducing model size and computational requirements while maintaining acceptable performance. This paper explores key techniques used to shrink LLMs for efficient execution on mobile hardware, including model pruning, quantization, knowledge distillation, parameter-efficient fine-tuning, low-rank factorization, and hardware-aware optimization. The study also discusses challenges, applications, and future research directions in edge AI deployment
Zitieren
APA
Vishwakarma, V. S. A. P. S. (2026). Edge AI Optimization: Techniques for Shrinking Large Language Models (LLMs) to Run Efficiently on Mobile Hardware. International Journal of Advanced Research in Science Communication and Technology, 267. https://doi.org/10.48175/ijarsct-37136
Vancouver
Vishwakarma VSAPS. Edge AI Optimization: Techniques for Shrinking Large Language Models (LLMs) to Run Efficiently on Mobile Hardware. International Journal of Advanced Research in Science Communication and Technology. 2026:267. doi:10.48175/ijarsct-37136
BibTeX
@article{Vishwakarma2026,
author = {Vishwakarma, Vaishnavi Siddhtekakar and Prof. Sandeep},
title = {Edge AI Optimization: Techniques for Shrinking Large Language Models (LLMs) to Run Efficiently on Mobile Hardware},
journal = {International Journal of Advanced Research in Science Communication and Technology},
year = {2026},
pages = {267},
doi = {10.48175/ijarsct-37136}
}
EUVIMED