The main objective of this study was to evaluate the effects of control-release fertilizer (CRF) on pollutant loadings from a small watershed. The Baran watershed, 386 ha in size, was selected as the study site, and the AGNPS (Agricultural Non-point Source Pollution) model was used to evaluate the effects of fertilizer types. Digital maps of digital elevation (DEM), slope distribution, channel, flow direction, landuse, soil, and curve number were extracted from the study watershed. Model parameters related to hydrology and water quality were calibrated and validated by comparing model predictions with the observed data collected for 2 years (1999 to 2000). Calibration and validation resulted in $R^2$ values of 0.75-0.91 for all the water quality parameters. All the paddy fields (21.2 %) of the study watershed were sprayed by either CRF or NPK (standard fertilizer). In CRF application, total nitrogen (TN) load was 4.9% less than NPK application, however total phosphorus (TP) load was 0.7 % more than NPK application. In CRF application, considering only paddy fields in the study area, TN load was 38.7 % less than NPK application. Using CRF in paddy fields could be one of the ways to reduce pollutant loadings from agricultural watersheds, however, in order to confirm it, more researches about effects of using CRF are necessary.