TabPFN Launches Open-Source Foundation Model for Tabular Data with Cloud and Local Inference Options

TabPFN launches as an open-source foundation model for tabular data, supporting classification and regression tasks with both local PyTorch and cloud-based inference, while enterprise users gain access to large-scale data support handling up to 10 million rows.

• TabPFN is an open-source foundation model for tabular data that supports both classification and regression tasks, offering local PyTorch inference with GPU support or cloud-based inference via a client API.
• The model works best on datasets with fewer than 100,000 samples and 2,000 features, and an ecosystem of extensions provides advanced capabilities including interpretability tools, unsupervised learning, hyperparameter optimization, and post-hoc ensembling.
• TabPFN-2.5 and TabPFN-2.6 model weights are available under a non-commercial license, while an Enterprise Edition offers fast inference, large-scale data support up to 10 million rows, and commercial licensing options.