Email spam is one of the main issues with today’s Internet, which may financially harm businesses and other individual consumers. Due to its affordable sending costs, ease of use from anywhere globally, and speedy message delivery, email is a widely used and well-received communication. The rise of email-based attacks is directly related to weaknesses in email protocol as well as the volume of financial and electronic commercial activities. The advancement of algorithms for Quantum Machine Learning (QML) and quantum computing (QC) has begun to show exponential speedups. Quantum computing handles large datasets very well in the form of vectors and matrix operations. Lately, Quantum Machine learning for classification has been an important research agenda. In this study, the comparison between classical and quantum computing is carried out for spam base dataset. A binary class classification problem is implemented using classical models such as Support Vector Classifier (SVC), K-Nearest Neighbor (KNN), and Naive Bayes algorithm where SVC outperforms among these algorithms. Further classical SVC is compared with Quantum Support Vector Classifier (QSVC) and the findings show that the classical SVC perform notably better than the QSVC, with differences of 8% accuracy,7% precision,7% recall, and 8% F1-score. The study specifies that, when dealing with complex datasets, the QSVC method performs better than the classical SVC algorithm. The QSVC has outperformed the KNN and Naïve Bayes classical models.