This paper presents empirical evidence on the impact of patents on economic growth, in 8 countries of Latin America during the period 1990-2011. A Cobb-Douglas production function type is estimated to quantify the effect and magnitude that have patents registered by residents and patents registered by non-residents, on the GDP, controlling by variables as gross capital formation and labor force. The empirical results show that there is a significant positive relationship in which long-run impact of the registered residents on GDP is smaller than patents registered by non-resident about 0.02%.