Smart-tongue was used in quality identification of tartary buckwheat tea in different roasting temperatures, time, and storage periods. Platinum, gold, palladium, tungsten, titanium, and silver electrodes were used as working electrodes to detect the quality under different pulse frequencies of 1,0, and 100Hz. Moreover, principal component analysis (PCA) and linear discriminant analysis (LDA) were used for data analysis. The results showed that the quality of tartary buckwheat tea was significantly influenced by roasting temperature and the storage period. However, roasting time did not significantly affect the tea quality. PCA could distinguish tartary buckwheat tea produced under big temperature differences, but had nothing to do with tartary buckwheat tea produced under the same roasting temperature, different roasting time, and different storage periods. However, LDA could reflect the discrepancy in tartary buckwheat tea produced under different roasting temperatures and time (12 samples) and storage periods (7 samples), and the discrimination indexes (DI) were 99.8% and 99.7%.