Enzymes turnover substrates into products with amazing efficiency and selectivity and as such have great potential for use in biotechnology and pharmaceutical applications. However, details of their catalytic cycles and the origins surrounding the regio‐ and chemoselectivity of enzymatic reaction processes remain unknown, which makes the engineering of enzymes and their use in biotechnology challenging. Computational modelling can assist experimental work in the field and establish the factors that influence the reaction rates and the product distributions. A popular approach in modelling is the use of quantum mechanical cluster models of enzymes that take the first‐ and second coordination sphere of the enzyme active site into consideration. These QM cluster models are widely applied but often the results are dependent on model choice and selection. Herein, we show that QM cluster models can produce highly accurate results that reproduce experimental product distributions and free energies of activation, regarded that large cluster models with >300 atoms are used. In this tutorial review, we give general guidelines on the set‐up and applications of the QM cluster method and discuss its accuracy and reproducibility. Finally, several representative QM cluster model examples on metal‐containing enzymes are presented, which highlight the strength of the approach.