While Bayesian techniques are necessary for data analysis of CMB datasets, they are computationally unfeasible, since they require O(N^3) operations (where N is the number of pixels), which would require timescales of years on the fastest existing supercomputing grids for the PLANCK dataset, for instance. Gibbs' sampling is a fast and efficient Markov Chain Monte Carlo technique that has been applied successfully for Bayesian analysis of imaging CMB experiments. I will discuss the application of Gibbs' sampling to interferometric CMB datasets.