Prediction of financial instruments to create enormous wealth has been a source of fascination since the dawn of capitalism in the world. The objective of this study is to improvise over the current research for prediction and forecasting attempts. This paper methodology predicts the close price of National Stock Exchange 50 using quantum machine-learning and hybrid quantum–classical model QLSTM (Quantum Long Short-Term Memory). QLSTM achieves quantum benefits by combining LSTM with Variational Quantum Circuits (VQC). The proposed methodology has been compared with Bi-directional LSTM (BiLSTM), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Feedforward Neural Network (FNN). Mean Squared Error (MSE), Root MSE (RMSE), Mean Absolute Percentage Error (MAPE), Weighted MAPE (WMAPE), Symmetric MAPE (SMAPE) and R2 score has been taken as the evaluation criteria. QLSTM achieved an impressive R2 score of 0.9804, which has been taken as the primary metric. It also had the best MSE and RMSE errors of 116,461.40 and 341.26 with the lowest MAPE, WMAPE, and SMAPE of 0.0176, 0.0195, and 0.0178, respectively. The proposed approach improved the R2 Score by 6–7% over the next best model considered in the study. Other metrics as well confirm the advantages of Quantum LSTM.