Agriculture supports food security by producing the crops and livestock needed to feed the population. It provide employment to a large share of the population, especially in rural areas. This work present a Hybrid Quatnum integrated with CNN model compare with Hybrid CNN-Transformer model for classify soil image. Then suggest best corp with fertilizer according to predicted soil type. There used soil type are Alluvial, Black, Clayey, Red and Sandy. There evaluate accuracy, confusion matrix, classification report and mismatch detection of both model to find best model. Among them the HQCNN model achieved 94% training accuracy with 92% validation accuracy and also 93% test accuracy. There used a excel dataset including Urea, DAP, Potash, and SSP. Developed a friendly web application for farmer to get advantage of this proposed work.