The Weather Research and Forecasting (WRF) model is widely used as a regional climate model for dynamical downscaling in many regions world-wide. This study evaluates the WRF model for regional climate applications over Thailand, focusing on simulated precipitation using various convective parameterization schemes available in WRF. The NCEP/NCAR Reanalysis are used as forcing boundary data. The WRF simulations were performed at a 20-km grid spacing with an outer 60-km nest, to which the boundary forcing was applied. Experiments are presented for the year 2005 using four convective cumulus parameterization schemes, namely, BMJ (Betts-Miller-Janjic), GD (Grell-Devenyi), G3D (improved Grell-Denenyi) and KF (Kain-Fritsch) with and without nudging applied to the outermost nest. Results are evaluated both against station data and gridded observations. In general, the experiments with nudging perform better than un-nudged experiments and the BMJ cumulus scheme with nudging yields the smallest bias relative to observations.