To add, I'll be downloadading a few of several model runs from a dataset of publicly available downscaling experiments. I'll then analyze each climate model, and then average the results of each experiment to form an ensemble. It is known that one should not average GCM runs until the final step in one's analysis.
My advice is to spend a day picking temperature trends from the WB-CMIP model portal for a wide range of environments, and only then draw your conclusions.