The effects of the land cover changes have impacted on the stream flow of the watershed by changing the magnitude of surface runoff and ground water flow. This study evaluates the impact of land use/land cover change dynamics on Gelda stream using Soil and Water Assessment Tool (SWAT) and Soil and Water Assessment Tool calibration and uncertainty program (SWAT-CUP) models in Gelda watershed. Environment for visualizing images (ENVI) 5.1 and Arc Geographic information system 10.4.1 were used to generate land use land cover maps from Landsat Thematic mapper, Enhanced Thematic mapper plus, and Operational land imager developed, respectively, in 1984, 2000, and 2016. The land cover maps were generated using the Maximum Likelihood Algorithm of Supervised Classification. The accuracy of the classified maps was assessed using Confusion Metrics. Change detection was done by using ENVI 5.1 software. The result of this analysis showed that the agricultural land and settlement area have expanded during the study period of 1984 to 2016. During this study, most parts of the grazing land and vegetative covers were changed to agricultural land (14.32%). An increase of agricultural land by 32.23 % over 33year‟s period (1984- 2016) resulted in a change of stream flow. In the change detection analysis from this study between 1984 and 2016, the sum of forest (7.74%), bush (10.71%), and grazing lands (14.32%) were significantly changed to agricultural land by 32.77% whereas the sum of the forest (0.11 %), bush (0.42 %), and grazing lands (0.6 %) were changed to built-up area by 1.14 %. The performance of the SWAT model was evaluated through sensitivity analysis, calibration, and validation. Ten flow parameters were identified to be sensitive for the stream flow of the study area and used for model calibration. Model calibration and validation for stream flow were done for 20 (1987-2006) and 10 (2007-2016) years starting after three years warm up period respectively. The performance of the model was checked for daily and monthly setup. The Daily calibration and validation results were in good agreement between measured and simulated flow with the coefficient of determination (R2) of 0.79, Nash Sutcliffe efficiency (NSE) of 0.75, and percent bias (PBIAS) of 0.12 for calibration, and R2 of 0.76, NSE of 0.72, and PBIAS of 0.14 for validation. The monthly calibration and validation results showed that a very good agreement between measured and simulated flow with R2 of 0.86, NSE of 0.81 and PBIAS of 0.08 for calibration, and R2 of 0.88, NSE of 0.78, and PBIAS of 0.11 for validation. The analysis indicated that the stream flow during the wet months has increased, while the flow during the dry months has decreased. The surface runoff increased, while groundwater flow decreased from the year 1984-2016 due to expansion of agricultural land, extraction of ground water and expansion of small scale irrigation. The model results showed that the stream flow characteristics was changed due to the land use land cover change during the study periods from1984-2016.