Checkpointing is a technique that is often employed for granting fault tolerance for applications executing in failure-prone environments. It consists on regularly saving the application’s state in another and fault independent storage such that if the application fails, it can be continued without necessarily restarting it. In this context, fixing the checkpointing frequency is an important topic which we address in this paper. We particularly address this issue considering hybrid fault tolerance and variable size checkpoint dumps. We then evaluate our solution and compare it with state of the art models, and show that our solution brings better results.