NEWS · MODELS · #2398
IBM publishes Granite timeseries ensemble recipe with probabilistic and IQR aggregation
IBM's Granite TSFM provides a permissively licensed ensemble recipe that combines four pre-trained Granite architectures to produce median and quantile forecasts without retraining or fitted ensemble weights. Two aggregation recipes are available — a default Probabilistic Ensemble (uniform probability pooling) and an IQR-based weighting variant — downloadable via Hugging Face and evaluated across 97 GIFT-Eval configurations with leaderboard scores captured on 20 October 2026.
KEY POINTS
- IBM's Granite TSFM provides a permissively licensed ensemble recipe that combines four pre-trained Granite architectures to produce median and quantile forecasts without retraining or fitted ensemble weights.
- Two aggregation recipes are available — a default Probabilistic Ensemble (uniform probability pooling) and an IQR-based weighting variant — downloadable via Hugging Face and evaluated across 97 GIFT-Eval configurations with leaderboard scores captured on 20 October 2026.
- Provides a ready-to-use, permissively licensed default for probabilistic time-series forecasting that reduces model-choice risk and requires no fine-tuning, with benchmark evaluations for guidance.
WHY IT MATTERS
Provides a ready-to-use, permissively licensed default for probabilistic time-series forecasting that reduces model-choice risk and requires no fine-tuning, with benchmark evaluations for guidance.