Electronic waste (E-waste) is a rapidly growing global issue driven by the increasing consumption of electronic devices due to massive technological upgradation. E-waste contains both useful and hazardous materials, so it is important to handle it properly in an environment friendly manner and get back valuable resources. E-waste classification is crucial for effective recycling and disposal processes. This study investigates the performance of various deep learning models, namely VGG16, VGG19, Inception v3, and YOLO v8, in classifying e-waste into six categories: monitor, mobile, mouse, keyboard, laptop, and others. The dataset comprises 720 training images, 60 validation images, and 60 test images. Transfer learning technique is employed, and models are trained at different epochs on the same dataset. The performance of various models is evaluated using accuracy and speed. Results indicate that YOLO v8 outperforms other models in terms of accuracy and speed. This study aids the research in e-waste management. The results of this study can be used to automate the classification of e-waste, thereby dealing with the increasing issue of electronic waste in the digital era.