This research aims to evaluate the specific energy consumption in marble machining processes performed by CNC machines. The main objective of the study is to provide an analytical framework for improving energy efficiency in CNC machining processes by investigating the effects of process parameters—especially the material removal rate (MRR) factor—on the specific energy. The experiments were conducted on CNC machines with different machining parameters. In the data collection process, the data obtained using a load meter tester were transferred to a modeling program in STL file format by three-dimensional laser scanning technology. Effective cutting parameters such as Fc, Ft, Ec and Se were used to monitor the performance of the cutting tools. In this study, the evaluation of energy consumption was planned using common machine learning models such as XGBoost, Gradient Boosting, Random Forest and LightGBM. The findings show that MRR produces significant differences on specific energy, while XGBoost and Gradient Boosting models perform the best in specific energy predictions. In conclusion, this study is an important step towards managing and optimizing specific energy consumption during marble processing on CNC machine. The findings obtained with machine learning models will make a valuable contribution to improve energy efficiency and environmental sustainability in industrial applications.