# IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license

DevFeed: [IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license](<https://devfeed.tech/articles/ibm-releases-sota-granite-time-series-patchtst-fm-r2-model-with-commercial-friendly-license-7266.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/ibm-research/ibm-releases-sota-granite-time-series>)

Author: Roman Vaculin; Wesley M Gifford; Jiri Navratil; Chandra Reddy; Ayhan Sebin

Published: 2026-09-09T15:36:24Z

Content type: release

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [foundation-models](<https://devfeed.tech/topics/foundation-models.md>), [Temporal data](<https://devfeed.tech/topics/temporal-data.md>), [releases](<https://devfeed.tech/topics/releases.md>), [benchmarking](<https://devfeed.tech/topics/benchmarking.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [Inference](<https://devfeed.tech/topics/inference.md>)

Tags: [apache](<https://devfeed.tech/tags/apache.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [foundation-models](<https://devfeed.tech/tags/foundation-models.md>), [ibm](<https://devfeed.tech/tags/ibm.md>), [inference](<https://devfeed.tech/tags/inference.md>), [model-architecture](<https://devfeed.tech/tags/model-architecture.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [releases](<https://devfeed.tech/tags/releases.md>), [time-series](<https://devfeed.tech/tags/time-series.md>), [zero-shot](<https://devfeed.tech/tags/zero-shot.md>)

## AI overview

IBM released Granite Time Series PatchTST-FM-r2, a roughly 385M-parameter time-series foundation model for zero-shot forecasting. The article covers its architecture, probabilistic forecasting, missing-value imputation, benchmark results, licensing, and available reproducibility resources.

## Source excerpt

Time-series foundation models are changing the way forecasting systems are built. Instead of training and maintaining a separate model for every dataset, users can use a pretrained model and generate forecasts zero-shot. IBM has released Granite Time Series PatchTST-FM-r2, the latest model in the Granite TSFM family (github, blog).