IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license
Which summary reads better? Pick one — models revealed after.Both summaries are AI-generated.
IBM's Granite Time Series PatchTST-FM-r2 achieves state-of-the-art zero-shot forecasting performance with 385M parameters, outperforming replicable zero-shot models on the GIFT-Eval benchmark under a commercial-friendly Apache 2.0 license. This enables enterprises to deploy a single pretrained model for diverse time-series forecasting tasks—like demand, traffic, or telemetry—without costly dataset-specific training, reducing deployment overhead while maintaining high accuracy.
The Granite Time Series PatchTST-FM-r2 model has 385M parameters and achieves top zero-shot forecasting performance on the GIFT-Eval benchmark under a commercial-friendly Apache 2.0 license, enabling production-ready, general-purpose forecasting for various time series applications without requiring dataset-specific model training. This allows teams shipping LLM and agent-based systems to integrate high-performance, flexible forecasting capabilities without licensing constraints, directly leveraging the model's open weights and inference pipeline.