Malcom: Indonesian Journal of Machine Learning and Computer Science
Vol. 6 No. 4 (2026): MALCOM October 2026

Multi-GPU Benchmarking of YOLO Generations for PCB Defect Detection

Maghribi, Mohammad Maulana (Unknown)
Rochim, Febry Putra (Unknown)



Article Info

Publish Date
30 Oct 2026

Abstract

Thorough defect detection on printed circuit boards (PCBs) is required to ensure manufacturing quality and reliability. Even though many modern YOLO-based detectors exist, very little research focuses on comparative evaluation across multiple YOLO generations while accounting for deployment-related factors such as training costs, hardware limitations, and energy efficiency. Twelve model configurations from YOLOv8, YOLO11, YOLOv12, and YOLO26 generations have been benchmarked in this study on a dataset of 10,628 images representing six types of PCB defects. All the configurations have been trained under similar conditions, including transfer learning and data augmentation. Metrics utilized in the performance assessment include Precision, Recall, F1-score, mAP@0.5, and mAP@0.5:0.95. Deployment analysis considers inference speed, training time, VRAM usage, GPU speedup, and energy consumption for NVIDIA RTX 3060, RTX 5060 Ti, and RTX 4090 GPUs. All models achieved excellent detection performance, with mAP@0.5 ranging from 0.985 to 0.989. YOLOv8m obtained the highest mAP@0.5:0.95 value of 0.697. RTX 5060 Ti demonstrated the best balance between training speed and energy efficiency, while RTX 4090 showed the highest acceleration for complex models. The current research is the first to provide multi-GPU and multi-YOLO benchmarking for real-life PCB defect detection in industrial PCB inspection.

Copyrights © 2026






Journal Info

Abbrev

malcom

Publisher

Subject

Computer Science & IT

Description

MALCOM: Indonesian Journal of Machine Learning and Computer Science is a scientific journal published by the Institut Riset dan Publikasi Indonesia (IRPI) in collaboration with several Universities throughout Riau and Indonesia. MALCOM will be published 2 (two) times a year, April and October, each ...