Simulated Annealing, a wide-spread technique for combinatorial optimisation, is employed to find the optimal candidate in a candidate set, as defined in Optimality Theory (OT). Being a heuristic techniques, simulated annealing does not guarantee to return the correct solution, and yet, some result is always returned within a constant time. Similarly to language production, this time framework can be diminished with the cost of diminishing correctness. We demonstrate how simulated annealing can model linguistic performance, built upon a competence theory, namely, OT. After having applied simulated annealing to OT, we attempt to reproduce empirical observations on metrical stress in Dutch fast speech. Simulated annealing necessitates defining a topology on the candidate set, as well as an exact formulation of the constraint OUTPUTOUTPUT CORRESPONDENCE.