Credit and market risks are crucial for financial institutions. In this paper we present the model used by the Central Bank of Chile to conduct the stress tests for commercial banks in Chile. Market risk uses a balance-sheet approach that is consistent with the credit risk. For exchange rate risk we consider a change in the value of the portfolio under an unexpected change in the exchange rate by X%, meanwhile the interest rate risk is computed using a model for the whole yield curve. In particular, the modeling of this risk follows Nelson and Siegel (1987). Credit risk is computed using a non-linear VAR that relates banking system aggregates (loan loss provisions, credit growth, and write-offs) with macroeconomics variables (output growth, short and long term interest rates, terms of trade, and unemployment). For each Financial Stability Report (FSR) the model is calibrated using data from 1997 to the most recent date at monthly frequency. The effect on individual banks is computed adjusting the loan loss provision and total loans of each bank with the forecast value for the system. Given that forecasts are separated by type of loans (commercial, mortgage, and consumer) then the final effect on a particular bank depend on its initial composition.