We introduce an inference method based on quantiles matching, which is useful for situations where the density function does not have a closed form -but it is simple to simulateand/or moments do not exist. Functions of theoretical quantiles, which depend on the parameters of the assumed probability law, are matched with sample quantiles, which depend on observations. Since the theoretical quantiles may not be available analytically, the optimization is based on simulations. We illustrate the method with the estimation of α-stable distributions. A thorough Monte Carlo study and an illustration to 22 financial indexes show the usefulness of the method.Keywords: Quantiles, simulated methods, α-stable distribution, fat tails. We are grateful to Marcelo Fernandes, Marc Hallin and Marc Paolella, as well as the participants at the conferences in "recent developments in time series" (Rennes, France) and in "statistical inference in multivariate models and time-series models" (Kagoshima, Japan), the ECORE-KUL seminar, and the doctoral course on "fat-tailed distributions" in the University of Zurich for insightful remarks.