This paper generalizes Kunert and Martin's (Ann Stat 28:1728-1742, 2000) method for finding optimal designs under a fixed interference model, to find optimal designs under a mixed interference model. The results are based on the properties of information matrices in fixed and mixed models given in Markiewicz (J Stat Plan Inference 59:127-137, 1997). The method is applied to find a design which is optimal for any given variances of random neighbor effects.