TiRex-2 is a pretrained time series foundation model that forecasts one or many target
variates directly from their history, optionally conditioned on past and future-known
covariates. A single checkpoint serves both univariate and multivariate forecasting and
operates in a streaming fashion as new observations arrive — all zero-shot, with no
task-specific training or fine-tuning.
TiRex-2 generalizes our original univariate model, TiRex, to
multivariate forecasting with past and future covariates.
Key facts
Zero-shot multivariate forecasting:
TiRex-2 forecasts multiple target variates out of the box, without training or fine-tuning on you data.
Past and future-known covariates:
TiRex-2 natively conditions on past covariates and future-known covariates, such as
calendar features, holidays, promotions, or scheduled interventions.
Small active footprint:
TiRex-2 activates 38.4M parameters in univariate mode and an additional 44.1M parameters
for multivariate forecasting.
Getting started
📖 For a detailed guide — including pip installation, a Google Colab demo, covariate
examples, and benchmark reproduction — see our GitHub repository.
The environment is managed by Pixi. Run the following to install it on your machine
bash
1curl -fsSL https://pixi.sh/install.sh |sh2git clone https://github.com/NX-AI/tirex-2 &&cd tirex-2
3# activate the cpu-only env4eval"$(pixi shell-hook -e example)"# to execute on GPUs use `example-cu128` or `example-cu126`
Minimal usage predicting a simple sine wave:
python
1import matplotlib.pyplot as plt, torch
2from tirex2 import TimeseriesType, load_model
34model = load_model("NX-AI/TiRex-2", device="cpu")# use `device="cuda"` if cuda is available5y = torch.sin(torch.arange(160).float()/8)6ts = TimeseriesType(target=y[:128].unsqueeze(0), past_covariates=None, future_covariates=None)7forecast = model.forecast([ts], prediction_length=32, output_type="numpy")[0][0]
We provide predefined Pixi tasks showcasing examplary forecasts. These run in the CPU-only example environment by default:
pixi run minimal runs above code and creates a plot of the forecast.
pixi run comparison showcases the additional benefit of future known covariates in forecasting a target.
For a more interactive demo of TiRex-2, we also provide a quick-start notebook.
TiRex-2 Pro
TiRex-2 already provides state-of-the-art performance for zero-shot prediction, so you can use this open-source release without training on your own data.
Our pro version extends TiRex-2 with additional capabilities, including:
Streaming: incremental forecast updates as new observations arrive, without recomputing over the full history.
Speed: performance-optimized inference, including optimization for dedicated hardware such as edge, embedded, and industrial PC deployments.
Finetuning: models fine-tuned on your data or with different pretraining.
Classification & Regression: TiRex-2 adapted for classification and regression tasks.
If you are interested in any of these, please contact us at contact@nx-ai.com.
Cite
If you use TiRex-2 in your research, please cite our work:
bibtex
1@misc{podest2026tirex2generalizingtirexmultivariate,
2 title={TiRex-2: Generalizing TiRex to Multivariate Data and Streaming},
3 author={Patrick Podest and Marco Pichler and Elias Bürger and Levente Zólyomi and Bernhard Voggenberger and Wilhelm Berghammer and Daniel Klotz and Sebastian Böck and Günter Klambauer and Sepp Hochreiter},
4 year={2026},
5 eprint={2607.01204},
6 archivePrefix={arXiv},
7 primaryClass={cs.LG},
8 url={https://arxiv.org/abs/2607.01204},
9}
Other versions:
Alongside this pretrained checkpoint, we release decontaminated versions to enable fair
zero-shot evaluation on specific benchmarks by excluding their data from pretraining:
