Evaluating Machine LearningWorkloads inWebAssembly: A Comparison of Browser-Based Runtimes Using Python

WebAssembly (WASM) has emerged as a transformative technology, enabling the deployment of high-performance applications across diverse platforms, including web environments traditionally unsuited for computationally intensive tasks. Despite extensive research on its general performance characteristics, the execution of machine learning (ML) workloads in browser-based Python runtimes is still in an early exploratory phase. This study presents a systematic evaluation of three ML models, K-Means, Logistic Regression, and Naïve Bayes—executed in-browser using two Pythonbased WASM runtimes: Pyodide and PyScript. The findings highlight the practicality of deploying ML workloads in browser-based environments using WASM and provide insights into the trade-offs between runtime efficiency and model performance.