Quantum Machine Learning (QML) provides new opportunities for data analysis in high-energy physics. This study investigates the use of QML techniques for b-jet charge tagging at LHCb, focusing on a Variational Quantum Classifier algorithm. By utilising quantum entanglement and correlations among jet particles, the quantum approach aims to improve tagging performance compared to traditional methods. A dataset of b-jets at a center-of-mass energy of 13 TeV was used. Quantum models were compared against a Deep Neural Network (DNN) and conventional muon-based technique (muon-tag). The results show that quantum models perform competitively on reduced datasets, demonstrating their potential for computationally constrained tasks. This work represents an important step in combining quantum computing with machine learning for particle physics, opening pathways for future studies on forward-central b-jet asymmetry and related applications.