amazon-science / chronos-forecasting

Chronos: Pretrained Models for Time Series Forecasting 🚀 News • **30 Dec 2025**: ☁️ Deploy Chronos-2 to AWS with Amazon SageMaker: new guide covers real-time inference (GPU/CPU), serverless endpoints with automatic scaling, and batch transform for large-scale forecasting. See the deployment tutorial. • **20 Oct 2025**: 🚀 Chronos-2 released. It offers _zero-shot_ support for univariate, multivariate, and covariate-informed forecasting tasks. Chronos-2 achieves the best performance on fev-bench, GIFT-Eval and Chronos Benchmark II amongst pretrained models. Check out this notebook to get started with Chronos-2. • **12 Dec 2024**: 📊 We released , a lightweight package for benchmarking time series forecasting models based on the Hugging Face library. • **26 Nov 2024**: ⚡️ Chronos-Bolt models released on HuggingFace. Chronos-Bolt models are more accurate (5% lower error), up to 250x faster and 20x more memory efficient than the original Chronos models of the same size! • **13 Mar 2024**: 🚀 Chronos paper and inference code released. ✨ Introduction This package provides an interface to the Chronos family of **pretrained time series forecasting models**. The following model types are supported. • **Chronos-2**: Our latest model with significantly enhanced capabilities. It offers zero-shot support for univariate, multivariate, and covariate-informed forecasting tasks. Chronos-2 delivers state-of-the-art zero-shot performance across multiple benchmarks (including fev-bench and GIFT-Eval), with the largest improvements observed on tasks that include exogenous features. It also achieves a win rate of over 90% against Chronos-Bolt in head-to-head comparisons. To learn more about Chronos, check out the technical report. • **Chronos-Bolt**: A patch-based variant of Chronos. It chunks the historical time series context into patches of multiple observations, which are then input into the encoder. The decoder then uses these representations to directly generate quantile forecasts across multiple future steps—a method known as direct multi-step forecasting. Chronos-Bolt models are up to 250 times faster and 20 times more memory-efficient than the original Chronos models of the same size. To learn more about Chronos-Bolt, check out this blog post. • **Chronos**: The original Chronos family which is based on language model architectures. A time series is transformed into a sequence of tokens via scaling and quantization, and a language model is trained on these tokens using the cross-entropy loss. Once trained, probabilistic forecasts are obtained by sampling multiple future trajectories given the historical context. To learn more about Chronos, check out the publication. Available Models | Model ID | Parameters | | ---------------------------------------------------------------------- | ---------- | | | 120M | | | 120M | | | 28M | | | 9M | | | 21M | | | 48M | | | 205M | | | 8M | | | 20M | | | 46M | | | 200M | | | 710M | 📈 Usage To perform inference with Chronos, the easiest way is to install this package through : > [!TIP] > For reliable production use, we recommend using Chronos-2 models through Amazon SageMaker JumpStart. Check out this tutorial to learn how to deploy Chronos-2 inference endpoints to AWS with just a few lines of code. Forecasting A minimal example showing how to perform forecasting using Chronos-2: We can now visualize the forecast: Example Notebooks • Chronos-2 Quick Start     • Deploy Chronos-2 on Amazon SageMaker 📝 Citation If you find Chronos models useful for your research, please consider citing the associated papers: 🛡️ Security See CONTRIBUTING for more information. 📃 License This project is licensed under the Apache-2.0 License.