Kidney stones are solid mineral and salt deposits formed within the kidneys, causing excruciating discomfort and pain when they obstruct the urinary tract. The presence of speckle noise in CT-scan images, coupled with the limitations of manual interpretation, makes kidney stone detection challenging and highlighting the need for precise and efficient diagnosis. This research investigates the efficacy of YOLOv8 models for kidney stone detection, aiming to strike a balance between computational efficiency and detection accuracy. This study's novel evaluation framework and practical deployment considerations underscore its contributions to advance kidney stone detection technologies. It evaluates five YOLOv8 variants (nano, small, medium, large, and extra-large) using standard metrics such as precision, recall, F1-score, and mAP@50, alongside computational resources like training time, power consumption, and memory usage. The comprehensive evaluation reveals that while YOLOv8s and YOLOv8e demonstrate superior performance in traditional metrics, YOLOv8s emerges as the optimal model, offering a harmonious balance with its high precision (0.917), highest mAP@50 (0.918), moderate power consumption (150W), and efficient memory usage. Graphical analyses further elucidate the behaviour of each model across different confidence thresholds, confirming the robustness of YOLOv8s. Additionally, this research explores the impact of model size and complexity on inference speed, demonstrating that smaller YOLOv8 variants achieve real-time performance with minimal latency. The study also introduces a method for model scalability, allowing for adjustments in accuracy and computational demand based on specific clinical or resource constraints. These contributions further emphasize the importance of holistic model assessment for real-world medical applications.