Monkeypox, a zoonotic disease similar to smallpox, poses a significant public health challenge in Central and West African countries. To enhance early detection and timely intervention for effective management, developing efficient and accessible diagnostic tools becomes essential in addressing this significant public health concern. This study explores the precise detection of Monkeypox manifestations using deep learning models. In contrast, the custom lightweight CNN model is proposed, and it strikes an ideal balance between accuracy and run-time complexities, making it suitable for resource-limited settings and real-time applications. These findings contribute to early detection, accurate diagnosis, and effective control of Monkeypox disease. Through transfer learning and fine-tuning, the performance of these deep learning models is compared with the state of the art for disease classification. The proposed CNN model outperforms other models and achieves an impressive 98.13% accuracy.