2026-07-29T10:09:19Zhttps://ebiltegia.mondragon.edu/oai/request

oai:ebiltegia.mondragon.edu:20.500.11984/146522026-07-28T06:15:50Zcom_20.500.11984_1143com_20.500.11984_14090col_20.500.11984_1148

Illarramendi, Miren Agirre, Joseba Andoni Picatoste, Aitor Igartua, Juan Ignacio 2026-07-27T14:59:36Z 2026-07-27T14:59:36Z 2025 978-1-68558-311-8 2519-8483 https://katalogoa.mondragon.edu/janium-bin/janium_login_opac.pl?find&ficha_no=201250 https://hdl.handle.net/20.500.11984/14652 This research presents a comparative analysis of the performance of various Large Language Models (LLMs) for code generation tasks executed on Central Processing Units (CPUs) without the use of dedicated Graphics Processing Units (GPUs). The study evaluates key metrics including inference time, code generation accuracy, CPU and memory usage, and energy consumption. By conducting repeated experiments, we assess the impact of model size and optimization on efficiency in environments lacking GPU resources. Energy consumption is measured using tools like CodeCarbon, focusing on the environmental impact of running these models on CPU-based systems. The findings offer insights into the trade-offs between model precision, resource usage, and energy efficiency, providing valuable guidance for developers and researchers aiming to balance performance and sustainability in low-resource computing environments. eng © IARIA 2025 LLMs. GenIA GreenComputing Code Generation Energy Consumption Sustainability ODS 9 Industria, innovación e infraestructura Brains Without Brawn: Evaluating CPU Performance for Code Generation with Large Language Models