Abstract We consider a stochastic fire growth model, with the aim of predicting the behavior of large forest fires. Such a model can describe not only average growth, but also the variability of the growth. Fire is modeled as a random phenomenon on a regular spatial grid, specifically, an interacting particle system modeled as a continuous‐time Markov chain on a lattice. Each lattice site changes state according to local transition rates, which model the competing physical processes of fire spread, spotting, and burnout. The rate functions, which are currently tentative, could be based on topography, fuel moisture, and local weather. Implementing such a model in a computing environment allows one to obtain probability contour plots, burn size distributions, and distributions of time to specified events. Such a model also allows the incorporation of a stochastic spotting mechanism.