IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license
- ID
- 22830
- Status
- summarized
- Published
- 09 Sep 2026, 11:36 PM
- Fetched
- 10 Sep 2026, 1:08 AM
- Provider
- Hugging Face Blog
- Category
- developer-ai
- Original URL
- https://huggingface.co/blog/ibm-research/ibm-releases-sota-granite-time-series
- Source URL
- https://huggingface.co/blog/feed.xml
Summary
- Score
- 6.5
- Created
- 10 Sep 2026, 1:08 AM
- Tags
- Audience
- developersai_ml_learnerssaas_founders
What happened
IBM released Granite Time Series PatchTST-FM-r2, a ~385M-parameter time-series foundation model that achieves top zero-shot forecasting performance among replicable models with permissive licenses on the GIFT-Eval benchmark. It supports context lengths up to 8,192, probabilistic forecasting via a 99-quantile prediction head, missing-value imputation, and is dual-licensed under Apache-2.0 and OpenMDW-1.0.
Why it matters
If you build forecasting pipelines for demand, pricing, energy, traffic, or telemetry, you can now drop in a zero-shot model under a commercial-friendly license instead of training and maintaining per-dataset models. Weights, inference code, and benchmark reproduction scripts are all open, so you can evaluate it on your own data this week before committing.
Discussion angle
Whether zero-shot time-series foundation models are now practical enough to replace bespoke forecasting models in production, and where the gaps still are for Malaysian builders handling local demand or telemetry data.