In the Chinese language, a word consisting of one or more characters is a basic syntax-meaningful unit, however, each character in the word also has a definite meaning in itself. In this paper, we compare the perplexities of four n-gram language models (character-based bigram, character-based trigram, word-based bigram and class-based bigram) and their influence on the performance of contextual post-processing of Chinese scripts in an offline handwritten Chinese character recognition system. We also demonstrate the influence of the candidate set size on the performance of contextual post-processing in detail, and indicate that the number of candidates should vary with each script.