Definitely - IEDB among those in the public domain. Use it creatively. For instance in class II epitope prediction IEDB recommended is good but it is a constantly developing tool, e.g. now it seems that for DRB1*0101 and DRB1*1101 NetMHCIIpan method is optimal.
I second that NetMHCII can be good as well. depends what your interest is class I or classII. ClassII predictions are developing and are at times difficult to predict .