Efficient deployment of deep learning models on edge devices is critical for real-time applications. While 2:4 structured pruning has been recently studied in high-performance GPUs, its viability for edge devices has received less attention, despite its potential benefits in resource-constrained environments. This paper investigates its impact on performance, energy efficiency, and accuracy on the Nvidia Jetson Orin, leveraging the sparse tensor cores on this architecture to assess its practicality for edge computing. We conduct comprehensive experiments on several deep learning architectures, including convolutional neural networks and a transformer-based system. Our evaluation focuses on key metrics such as inference latency, power consumption, and predictive accuracy. The results indicate that 2:4 pruning has a reduced visible effect on performance and energy efficiency, except for residual networks and the transformer. However, the pruning technique demonstrates more promising results in terms of size reduction and accuracy recovery, with the ability to regain accuracy efficiently by adjusting the pruning criterion. These findings provide valuable insights into the trade-offs associated with sparsity-driven optimization and offer guidelines for deploying high-performance models in resource-constrained environments.