Optimizing land use allocation is a challenging task, as it involves multiple stakehold-ers with conflicting objectives. In addition, the solution space of the optimization growsexponentially as the size of the region and the resolution increase. This article presents anew ant colony optimization algorithm by incorporating multiple types of ants for solv-ing complex multiple land use allocation problems. A spatial exchange mechanism isused to deal with competition between different types of land use allocation. This mul-ti-type ant colony optimization optimal multiple land allocation (MACO-MLA) modelwas successfully applied to a case study in Panyu, Guangdong, China, a large regionwith an area of 1,454,285 cells. The proposed model took only about 25 minutes to find near-optimal solution in terms of overall suitability, compactness, and cost. Comparisonindicates that MACO-MLA can yield better performances than the simulated anneal-ing (SA) and the genetic algorithm (GA) methods. It is found that MACO-MLA hasan improvement of the total utility value over SA and GA methods by 4.5% and 1.3%,respectively. The computation time of this proposed model amounts to only 2.6% and 12.3%, respectively, of that of the SA and GA methods. The experiments have demon-strated that the proposed model was an efficient and effective optimization techniquefor generating optimal land use patterns.