TiRex

TiRex is NX-AI's xLSTM-based zero-shot forecasting model, a compact foundation forecaster that deliberately steps away from the Transformer backbone shared by most models in this catalog. The official card highlights strong short- and long-horizon performance together with support for both point and quantile forecasts, making it a capable general-purpose zero-shot option rather than a narrow specialist.

Architecturally it is a 35M-parameter xLSTM forecasting model, which gives it the recurrent-style in-context generalization behaviour that distinguishes it from attention-only designs. Its pretraining provenance is documented at a high level: the official card lists autogluon/chronos_datasets and Salesforce/GiftEvalPretrain as the main sources, without publishing a more exact mixture breakdown.

On TSFM.ai, reach for TiRex when you want a compact non-Transformer forecaster with strong in-context generalization and probabilistic output across short and long horizons. Step up to NX-AI/TiRex-1.1-gifteval when you want the newer TiRex 1.1 inference improvements and a pretraining mixture explicitly cleaned of GIFT-Eval overlap; the two share the same xLSTM architecture and 35M parameter count, so this base checkpoint is the simpler default and the 1.1 variant is the benchmark-hygiene-focused sibling.