Malicious attacks have been on the rise with the growth of technological innovations. With the increase in mali-cious attacks, many current defense systems focus on preventive and reactive measures. However, the Intrusion prevention system and Intrusion Detection system may not be able to detect all suspicious processes and files that come through the network. Even if the security system detects suspicious activity, it may be unable to quickly classify the type of malware to implement effective and efficient protection. Thus, much research has focused on creating machine-learning models to classify suspicious programs as malicious or benign. However, the limitation of classifying a suspicious file as benign or malicious still does not aid the system in deploying effective security measures to counteract the damage of executed suspicious files. We proposed to train machine learning models and deep learning models to classify the eight most common malware classes. Trained models that can classify malware classes will boost a system's efficiency in identifying the type of mal ware, focusing on the affected area, and deploying effective countermeasures to minimize damages. Our experiment shows that the XGBoost model performs the best for tabular data types with an average accuracy of 65%, and the Transformer model achieves the highest accuracy score of 57 % for sequential datasets.