Protein, oil content, stearic acid, linolenic acid, and linoleic acid are key indicators for evaluating the quality of flaxseed in order to optimize the detection method of nutritional quality of flaxseed and to improve the efficiency of the screening of high-quality flax germplasm resources. This study integrated visible near-infrared (Vis-NIR) and near-infrared (NIR) hyperspectral imaging to determine protein, oil, stearic acid, linolenic acid, and linoleic acid contents in diverse flaxseed varieties, along with conducting correlation analyses. After seven data preprocessing methods and three feature selection methods, quantitative prediction models were developed using partial least squares regression (PLSR), principal component regression (PCR), support vector regression (SVR), and multiple linear regression (MLR). Experimental results demonstrated that NIR and fused spectral data outperformed Vis-NIR data across all five quality indices. NIR spectroscopy showed optimal performance for predicting oil content (Rp2 = 0.9671, RMSEP = 0.4364 %), linolenic acid (Rp2 = 0.9517, RMSEP = 0.8795 %), and linoleic acid (Rp2 = 0.9458, RMSEP = 0.3037 %). Fused spectral data achieved superior predictions for protein content (Rp2 = 0.9712, RMSEP = 0.2360 %) and stearic acid (Rp2 = 0.9195, RMSEP = 0.3454 %). And the spatial distribution of flaxseed's internal nutrient contents was also visualized by map. The results showed that the NIR and fusion spectral sets could be successfully used to evaluate multiple nutritional qualities of flaxseed, which provides a new option for nondestructive determination of the nutritional qualities of flaxseed in the future.