An implementation of a Spanish POS tagger is described in this paper. This implementation combines three basic approaches: a single word tagger based on decision trees, a POS tagger based on variable memory Markov models, and a feature structures set of tags. Using decision trees for single word tagging allows the tagger to work without a lexicon that lists only possible tags. Moreover, it decreases the error rate because there are no unknown words. The feature structure set of tags is advantageous when the available training corpus is small and the tag set large, which can be the case with morphologically rich languages like Spanish. Finally, variable memory Markov models training is more efficient than traditional full-order Markov models and achieves better accuracy. In this implementation, 98.58% of tokens are correctly classified.