IBM’s 385M-Parameter Forecaster Pushes Zero-Shot Time Series Forward
Forecasting teams usually pay for accuracy by maintaining a separate model for every dataset. IBM’s Granite Time Series PatchTST-FM-r2 aims to change that: its roughly 385 million parameters handle zero-shot forecasts, missing-value imputation, and probabilistic outputs across demand, energy, traffic, and telemetry data. It ranks second among replicable zero-shot models on GIFT-Eval, with weights, inference code, and benchmark reproduction released under Apache 2.0 or OpenMDW 1.0.