Objective： The abnormal activation of the Fibroblast Growth Factor 19(FGF19) and Fibroblast Growth Factor Receptor 4 (FGFR4) signaling pathway promotes the proliferation of hepatocellular carcinoma cells, making FGFR4 one of the key targets for treating hepatocellular carcinoma. This study aims to elucidate the relationship between the structure and activity of quinazoline-based FGFR4 inhibitors using a three-dimensional quantitative structureactivity relationship (3D-QSAR) approach. Methods: 36 compounds were randomly divided into a training set and a test set. 3D-QSAR models were constructed using Comparative Molecular Field Analysis (CoMFA) and Comparative Molecular Similarity Indices Analysis (CoMSIA). Results: The cross-validation coefficients (q²) of the CoMFA and CoMSIA models were 0.735 and 0.680, respectively, and the fitting validation coefficients (r²) were 0.974 and 0.981, respectively. The predicted values of the two models were generally consistent with the experimental values,indicating that the models have predictive ability and good robustness. Conclusion: The contour maps illustrate the effects of different field effects on compound activity, providing insights for the design of novel quinazoline-based FGFR4 inhibitors.