One of the consequences of the climate change is the increase in the occurrence and intensity of heavy rainfall events. This condition leads to more frequent and severe urban flooding because of the increasing stormflow volumes that exceed the sewers capacity. In order to mitigate the risk of flooding in urban areas, sustainable urban drainage strategies have been proposed, and among these the use of green roofs. The potential of green roofs to manage urban stormwater has largely been proved. In light of this, modeling the hydrological behavior of vegetated covers appears a crucial issue for urban planners, policymakers and developers so as to quantify stormwater management ability of the green infrastructures before retrofitting existing buildings or planning new settlements. To predict the hydrological performances of a green roofs, different models with different levels of complexity have been introduced by several authors. Among these, the SWMM model has been here selected due to its widespread use and demonstrated efficiency. It has been compared using a number of goodness of fit indices with a basic transfer function approach, the Nash model, typically used to simulate the hydrological behavior of natural river basins and not yet fully explored for what concerns its implementation in predicting the runoff production from green roof systems. The two models have been calibrated against hourly data of thirteen rainfall-runoff events observed at two experimental green roofs, differing for the composition of the drainage layer, located in southern Italy, in a typical Mediterranean climate. Although the lower complexity and input data requirements that characterizes the Nash model, it returns interesting performances. Finally, the existence of a relationship between the errors and the rainfall characteristics has emerged.