Chronos-2

Chronos-2 is Amazon's universal successor to the original Chronos family, at 120M parameters. The official card frames it as a single model that handles univariate, multivariate, and covariate-informed forecasting in one architecture, a more general design than the univariate-first checkpoints of the first Chronos generation.

Under the hood it is a T5-inspired, encoder-only model that uses group attention and multi-step quantile decoding, so it can reason across related series and native covariates while emitting probabilistic forecasts directly. It is pretrained on a subset of Chronos Datasets, a subset of GIFT-Eval Pretrain, and synthetic univariate and multivariate data, as described by the official Chronos-2 card and technical report.

On TSFM.ai, Chronos-2 is the Chronos variant to choose when you need cross-learning across related series, native covariates, or broader zero-shot coverage than the earlier checkpoints offered. It is still a forecasting model rather than a general multi-task backbone, and carries a larger deployment footprint than the lightweight baselines; when you only need fast univariate quantile forecasts, the Chronos-Bolt checkpoints remain the cheaper, faster pick.