This study explores the therapeutic targets and mechanisms of Gynostemma pentaphyllum in non-alcoholic fatty liver disease (NAFLD). Using network analysis and bioinformatics, we identified target genes of Gynostemma's active metabolites in NAFLD through differential expression analysis, Weighted Gene Co-expression Network Analysis (WGCNA), and machine learning algorithms. From the intersection of 2,569 differentially expressed genes (DEGs), 1,279 key modular genes, and 532 target genes, 19 intersecting target genes were pinpointed, with PIM1, TYMS, and SLC29A1 identified as key targets. PIM1 was downregulated in NAFLD samples, while TYMS and SLC29A1 were upregulated. A nomogram based on these genes showed strong diagnostic potential for NAFLD. These genes were enriched in pathways related to spliceosome, lysosome, and purine metabolism. High infiltration levels of activated CD8 T cells, CD56bright natural killer cells, gamma delta T cells, and immature B cells were observed in NAFLD samples, negatively correlated with PIM1 and positively correlated with TYMS and SLC29A1. Single-cell analysis revealed higher PIM1 expression within annotated immune cell clusters. RT-qPCR confirmed that Gynostemma treatment modulated these gene expressions, increasing PIM1 while decreasing TYMS and SLC29A1. In vitro, Gynostemma pentaphyllum reduced lipid accumulation and triglyceride levels in FFA-induced hepatic steatosis models using HepG2, HuH7, and QSG7701 cells. These findings provide scientific insights into the therapeutic mechanisms of Gynostemma in NAFLD.