Introduction and Aims: Ionic models of cardiac action potentials (APs) may not reproduce all relevant datasets using their default settings, and tuning parameter values to improve fits may be difficult. To facilitate this task, we present CardioFit, a tool to fit cardiac AP model parameters to time-series data using particle swarm optimization (PSO). Methods: CardioFit can quickly find conductance parameter values for detailed human ventricular models, including those of ten Tusscher et al. (2006) and O'Hara et al., that match experimental data, within the capabilities of the models. CardioFit is implemented as a web-based tool using JavaScript and the WebGL graphics API, allowing PSO to take advantage of any available GPU hardware to run in parallel. As the PSO algorithm requires many candidate parameterizations to be evaluated simultaneously when searching for the best fit, this method is well-suited to large-scale parallelism. Results: Due to its fast parallel implementation, CardioFit can obtain conductance parameters of detailed ionic models to match a given dataset in a few minutes on consumer-grade hardware, although tens of thousands of model runs are typically required. As shown in the figure, these fits are able to reproduce the provided data within the capabilities of the selected model. Because CardioFit is a web-based tool, no installation or machine-specific setup is required; the tool runs at full speed on any machine with a modern web browser and graphics hardware. The interactive nature of the web-based interface allows expert users to set constraints on model parameters, while providing sensible default options for convenience. Conclusion: CardioFit is an efficient tool for quickly obtaining conductance parameter values for ionic models to reproduce data from cardiac experiments or other models.