The Tibetan Plateau (TP), known as the "Earth's Third Pole", has a fragile ecological environment, and is sensitive to global changes, which can easily lead to fluctuations of soil organic carbon (SOC). The spatial variations of soil organic carbon stocks (SOCS), and their driving factors in TP remain unclear. Here. we used quantile regression forest (QRF) model to map soil organic carbon density (SOCD) in TP at 90 m spatial resolution, and estimated the spatial uncertainty of the mapping. Generalized additive model (GAM) was used to analyze the nonlinear responses of SOCD to the driving factors. The results showed that the QRF model can explain about 32 %-51 % of SOCD variation, and the explanatory power decreased with increasing depth. The SOCD decreased gradually from southeast to northwest, and showed a decreasing trend with increasing depth. The SOCS of 0-100 cm soil was 37.26 Pg C of the entire TP, where the grassland occupied 54.59 % of the total stock. Vegetation and land surface temperature were important environmental covariates at all depths. SOCD has obvious nonlinear responses and threshold effects on temperature (MAAT), precipitation (MAP) and aridity (1-AI). The results are of great significance for understanding the status of SOC sequestration, and the response of SOCS in TP to climate conditions.