tabfm

Zero-shot forecasting, tabular classification, and regression via MCP — exposes Google TimesFM 2.5 and TabFM v1.0.0 to AI assistants. Just attach a CSV and describe what you want to predict.

Closing the Context Gap: Activation Alignment for Tabular In-Context Learning

R package for tabular foundation models: TabPFN, TabICL, and TabFM.

Can a tabular foundation model replace your training pipeline? Hands-on TabFM (Google) vs CatBoost vs GPT-6 Astra

Benchmarking, optimising and serving the TabFM tabular foundation model online: exact KV cache, torch.compile, FastAPI, Triton, KServe on kind and GKE

Visual interface for Google TabFM and Ollama for fast, local tabular data predictions

End-to-end machine learning and MLOps project for telco customer churn prediction. Compares, contrasts, and evaluates Logistic Regression, XGBoost, and TabFM.

Fine-tuning TabFM, Google's 1.64B tabular foundation model, on an Apple M4 laptop and on an NVIDIA L4 in GKE: zero-shot vs fine-tuned, laptop vs GPU

Does an account's company catch fraud the row model misses? Millions of real and synthetic transactions scored four ways: row only, graph features with XGBoost, a graph neural network, and Google's TabFM zero-shot. Graph features reach 96% of fan-in laundering vs 74% row-only; the GNN never beat them. Hop cost, drift, live latency. Demo below

Predict Palmer Penguins species with TabFM, Google's tabular foundation model — repeated random splits with accuracy and confusion-matrix reporting

Compare HistGB, LightGBM, CatBoost, AutoGluon, TabPFN, TabFM, and Kumo on tabular data. Inspect accuracy, disagreements, costs, and replacement risk.