Hyperspectral remote sensing sensors have the ability to capture a wide range of spectrum of ground objects with hundreds to thousands of bands. The obtained hyperspectral images contain more detailed spectral information than conventional panchromatic or color images. Hyperspectral classification plays a crucial role in remote sensing applications such as vegetation monitoring, land use analysis and environmental monitoring. Conventional deep learning models often struggle with limited labeled hyperspectral datasets and may not fully exploit complex spatial-spectral relationships. To address this gap, this study proposes a multi model transfer ensemble learning approach that combines the strengths of MobileNetV2 and ResNet-50 for enhanced classification. The methodology involves applying transfer learning using pre-trained MobileNetV2 and ResNet-50 models, followed by feature averaging and classification. To validate the efficacy of the proposed method, experiments were conducted on the Indian Pines, University of Pavia, and KSC hyperspectral datasets. The results prove that proposed method attains superior performance in classification.