# Time Series Forecasting Models: Open-Weight AI Source: https://savrn.com/models/tasks/time-series-forecasting Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- SAVRN Model Hub · Models by Task # Time Series Forecasting Models 64 open-weight time series forecasting models in the SAVRN Model Hub, with Autogluon, Amazon and Salesforce AI Research publishing the most. 64Models 18Publishers 616K to 2.5BParameter range 6Licenses ## SAVRN's Take Time series forecasting changed when foundation models arrived. Instead of training a model per series, you hand a pretrained model the history and it forecasts, often with no training at all. Amazon's Chronos family dominates this page, with Chronos-2 the most downloaded model in the category by far, alongside IBM's TinyTimeMixer, Google's TimesFM, Salesforce's Moirai and Datadog's Toto. These models are small, most under a billion parameters and many under a hundred million, so they run on CPUs and can forecast millions of series cheaply. The majority are Apache 2.0, but Salesforce's Moirai models are noncommercial. Forecasting is the one area where we insist on a backtest against your own history, compared with a simple seasonal baseline, before trusting any model with a decision. SAVRN Research, 2026-09-18 ## Most Downloaded | Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit | | --- | --- | --- | --- | --- | --- | | [chronos-2](https://savrn.com/models/chronos-2) | Amazon | 119M | apache-2.0 | 14.6M | 1x MI300X, $1.85/hr | | [chronos-2](https://savrn.com/models/chronos-2-2) | Autogluon | 119M | apache-2.0 | 12.9M | 1x MI300X, $1.85/hr | | [chronos-bolt-small](https://savrn.com/models/chronos-bolt-small) | Amazon | 48M | apache-2.0 | 6.5M | 1x MI300X, $1.85/hr | | [chronos-bolt-small](https://savrn.com/models/chronos-bolt-small-2) | Autogluon | 48M | apache-2.0 | 5.9M | 1x MI300X, $1.85/hr | | [chronos-2-small](https://savrn.com/models/chronos-2-small) | Autogluon | 28M | apache-2.0 | 2.8M | 1x MI300X, $1.85/hr | | [Kronos-Tokenizer-base](https://savrn.com/models/kronos-tokenizer-base) | ShiYu | 4M | mit | 2.5M | 1x MI300X, $1.85/hr | | [chronos-bolt-tiny](https://savrn.com/models/chronos-bolt-tiny) | Autogluon | 9M | apache-2.0 | 2.2M | 1x MI300X, $1.85/hr | | [chronos-bolt-base](https://savrn.com/models/chronos-bolt-base) | Autogluon | 205M | apache-2.0 | 1.7M | 1x MI300X, $1.85/hr | | [timesfm-2.5-200m-pytorch](https://savrn.com/models/timesfm-2-5-200m-pytorch) | Google | 231M | apache-2.0 | 1.7M | 1x MI300X, $1.85/hr | | [Kronos-small](https://savrn.com/models/kronos-small) | ShiYu | 25M | mit | 1.3M | 1x MI300X, $1.85/hr | ## Licenses | License | Models | Commercial use | | --- | --- | --- | | [apache-2.0](https://savrn.com/models/licenses/apache-2-0) | 40 | Yes | | [mit](https://savrn.com/models/licenses/mit) | 9 | Yes | | [cc-by-nc-4.0](https://savrn.com/models/licenses/cc-by-nc-4-0) | 8 | Not without separate permission | | other | 5 | Read the license | | [openmdw-1.0](https://savrn.com/models/licenses/openmdw-1-0) | 1 | Read the license | | [cc-by-nc-sa-4.0](https://savrn.com/models/licenses/cc-by-nc-sa-4-0) | 1 | Not without separate permission | ## Who Publishes Them | Publisher | Models | | --- | --- | | [Autogluon](https://savrn.com/model-publishers/autogluon) | 11 | | [Amazon](https://savrn.com/model-publishers/amazon) | 10 | | [Salesforce AI Research](https://savrn.com/model-publishers/salesforce) | 8 | | [IBM Granite](https://savrn.com/model-publishers/ibm-granite) | 7 | | [ShiYu](https://savrn.com/model-publishers/neoquasar) | 5 | | [Google](https://savrn.com/model-publishers/google) | 4 | ## All 64 Models, Page 1 of 2 Model · Time series forecasting ### [chronos-2](https://savrn.com/models/chronos-2) [Amazon](https://savrn.com/model-publishers/amazon) Update Jun 5, 2026: Deploy Chronos-2 on AWS with AutoGluon-Cloud. Real-time, serverless, or batch inference in 3 lines of code — pandas DataFrames in, forecasts out. Check out the new deployment guide. Chronos-2 is a 120M-parameter, encoder-only time series foundation model for zero-shot forecasting. It supports univariate, multivariate, and covariate-informed tasks within a single architecture. Inspired by the T5 encoder, Chronos-2 produces multi-step-ahead quantile forecasts and uses a group attention mechanism for efficient in-context learning across related series and covariates. Trained on a combination of real-world and large-scale synthetic datasets, it achieves state-of-the-art… Open weights apache-2.0 119M parameters chronos-forecasting [View model](https://savrn.com/models/chronos-2) Model · Time series forecasting ### [chronos-2](https://savrn.com/models/chronos-2-2) [Autogluon](https://savrn.com/model-publishers/autogluon) Update Jun 5, 2026: Deploy Chronos-2 on AWS with AutoGluon-Cloud. Real-time, serverless, or batch inference in 3 lines of code — pandas DataFrames in, forecasts out. Check out the new deployment guide. Chronos-2 is a 120M-parameter, encoder-only time series foundation model for zero-shot forecasting. It supports univariate, multivariate, and covariate-informed tasks within a single architecture. Inspired by the T5 encoder, Chronos-2 produces multi-step-ahead quantile forecasts and uses a group attention mechanism for efficient in-context learning across related series and covariates. Trained on a combination of real-world and large-scale synthetic datasets, it achieves state-of-the-art… Open weights apache-2.0 119M parameters chronos-forecasting [View model](https://savrn.com/models/chronos-2-2) Model · Time series forecasting ### [chronos-bolt-small](https://savrn.com/models/chronos-bolt-small) [Amazon](https://savrn.com/model-publishers/amazon) Update Feb 14, 2025: Chronos-Bolt models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Chronos-Bolt is a family of pretrained time series forecasting models which can be used for zero-shot forecasting. It is based on the T5 encoder-decoder architecture and has been trained on nearly 100 billion time series observations. 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… Open weights apache-2.0 48M parameters chronos-forecasting [View model](https://savrn.com/models/chronos-bolt-small) Model · Time series forecasting ### [chronos-bolt-small](https://savrn.com/models/chronos-bolt-small-2) [Autogluon](https://savrn.com/model-publishers/autogluon) Update Feb 14, 2025: Chronos-Bolt models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Chronos-Bolt is a family of pretrained time series forecasting models which can be used for zero-shot forecasting. It is based on the T5 encoder-decoder architecture and has been trained on nearly 100 billion time series observations. 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… Open weights apache-2.0 48M parameters [View model](https://savrn.com/models/chronos-bolt-small-2) Model · Time series forecasting ### [chronos-2-small](https://savrn.com/models/chronos-2-small) [Autogluon](https://savrn.com/model-publishers/autogluon) This is the small variant of the Chronos-2 model with 28M parameters. For usage and details on the Chronos-2 model, please refer to https://huggingface.co/autogluon/chronos-2. If you find Chronos-2 useful for your research, please consider citing the associated paper Open weights apache-2.0 28M parameters chronos-forecasting [View model](https://savrn.com/models/chronos-2-small) Model · Time series forecasting ### [Kronos-Tokenizer-base](https://savrn.com/models/kronos-tokenizer-base) [ShiYu](https://savrn.com/model-publishers/neoquasar) Kronos is the first open-source foundation model for financial candlesticks (K-lines), trained on data from over 45 global exchanges. It is designed to handle the unique, high-noise characteristics of financial data. Kronos is a family of decoder-only foundation models, pre-trained specifically for the "language" of financial markets—K-line sequences. It leverages a novel two-stage framework: 1. A specialized tokenizer first quantizes continuous, multi-dimensional K-line data (OHLCV) into hierarchical discrete tokens. 2. A large, autoregressive Transformer is then pre-trained on these tokens, enabling it to serve as a unified model for diverse quantitative tasks. The success of large-scale… Open weights mit 4M parameters pytorch [View model](https://savrn.com/models/kronos-tokenizer-base) Model · Time series forecasting ### [chronos-bolt-tiny](https://savrn.com/models/chronos-bolt-tiny) [Autogluon](https://savrn.com/model-publishers/autogluon) Update Feb 14, 2025: Chronos-Bolt models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Chronos-Bolt is a family of pretrained time series forecasting models which can be used for zero-shot forecasting. It is based on the T5 encoder-decoder architecture and has been trained on nearly 100 billion time series observations. 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… Open weights apache-2.0 9M parameters [View model](https://savrn.com/models/chronos-bolt-tiny) Model · Time series forecasting ### [chronos-bolt-base](https://savrn.com/models/chronos-bolt-base) [Autogluon](https://savrn.com/model-publishers/autogluon) Update Feb 14, 2025: Chronos-Bolt models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Chronos-Bolt is a family of pretrained time series forecasting models which can be used for zero-shot forecasting. It is based on the T5 encoder-decoder architecture and has been trained on nearly 100 billion time series observations. 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… Open weights apache-2.0 205M parameters [View model](https://savrn.com/models/chronos-bolt-base) Model · Time series forecasting ### [timesfm-2.5-200m-pytorch](https://savrn.com/models/timesfm-2-5-200m-pytorch) [Google](https://savrn.com/model-publishers/google) TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting. Please reinstall the latest version of the timesfm package to reflect these changes. Results should be unchanged. This checkpoint is not an officially supported Google product. See TimesFM in BigQuery for Google official support. timesfm-2.5-200m is the third open model checkpoint. timesfm-2.5-200m is pretrained using - Wikimedia Pageviews, cutoff Nov 2023 (see paper for details). - Google Trends top queries, cutoff EoY 2022 (see paper for details). - Synthetic and augmented data. At this point, please run Open weights apache-2.0 231M parameters timesfm [View model](https://savrn.com/models/timesfm-2-5-200m-pytorch) Model · Time series forecasting ### [Kronos-small](https://savrn.com/models/kronos-small) [ShiYu](https://savrn.com/model-publishers/neoquasar) Kronos is the first open-source foundation model for financial candlesticks (K-lines), trained on data from over 45 global exchanges. It is designed to handle the unique, high-noise characteristics of financial data. Kronos is a family of decoder-only foundation models, pre-trained specifically for the "language" of financial markets—K-line sequences. It leverages a novel two-stage framework: 1. A specialized tokenizer first quantizes continuous, multi-dimensional K-line data (OHLCV) into hierarchical discrete tokens. 2. A large, autoregressive Transformer is then pre-trained on these tokens, enabling it to serve as a unified model for diverse quantitative tasks. The success of large-scale… Open weights mit 25M parameters [View model](https://savrn.com/models/kronos-small) Model · Time series forecasting ### [Kronos-base](https://savrn.com/models/kronos-base) [ShiYu](https://savrn.com/model-publishers/neoquasar) Kronos is the first open-source foundation model for financial candlesticks (K-lines), trained on data from over 45 global exchanges. It is designed to handle the unique, high-noise characteristics of financial data. Kronos is a family of decoder-only foundation models, pre-trained specifically for the "language" of financial markets—K-line sequences. It leverages a novel two-stage framework: 1. A specialized tokenizer first quantizes continuous, multi-dimensional K-line data (OHLCV) into hierarchical discrete tokens. 2. A large, autoregressive Transformer is then pre-trained on these tokens, enabling it to serve as a unified model for diverse quantitative tasks. The success of large-scale… Open weights mit 102M parameters [View model](https://savrn.com/models/kronos-base) Model · Time series forecasting ### [timesfm-3.0-pytorch](https://savrn.com/models/timesfm-3-0-pytorch) [Google](https://savrn.com/model-publishers/google) TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting. This repository contains the official PyTorch weights and configurations for TimesFM 3.0. This model is released under the TimesFM Non-Commercial License v1.0. timesfm-3.0 is pretrained using - GiftEvalPretrain excluding the datasets that overlap with fev-bench - Wikipedia Pageviews, cutoff Nov 2023 (see paper for details). - Google Trends top queries, cutoff EoY 2022 (see paper for details). - Synthetic and augmented data. title={A decoder-only foundation model for time-series forecasting}, author={Das, Abhimanyu and Kong, Weihao and Sen, Rajat and… Open weights other 331M parameters [View model](https://savrn.com/models/timesfm-3-0-pytorch) Model · Time series forecasting ### [chronos-bolt-base](https://savrn.com/models/chronos-bolt-base-2) [Amazon](https://savrn.com/model-publishers/amazon) Update Feb 14, 2025: Chronos-Bolt models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Chronos-Bolt is a family of pretrained time series forecasting models which can be used for zero-shot forecasting. It is based on the T5 encoder-decoder architecture and has been trained on nearly 100 billion time series observations. 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… Open weights apache-2.0 205M parameters chronos-forecasting [View model](https://savrn.com/models/chronos-bolt-base-2) Model · Time series forecasting ### [chronos-t5-small](https://savrn.com/models/chronos-t5-small) [Amazon](https://savrn.com/model-publishers/amazon) Update Feb 14, 2025: Chronos-Bolt & original Chronos models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Update Nov 27, 2024: We have released Chronos-Bolt models that are more accurate (5% lower error), up to 250 times faster and 20 times more memory-efficient than the original Chronos models of the same size. Check out the new models here. Chronos is a family of pretrained time series forecasting models 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… Open weights apache-2.0 46M parameters chronos-forecasting [View model](https://savrn.com/models/chronos-t5-small) Model · Time series forecasting ### [chronos-bolt-tiny](https://savrn.com/models/chronos-bolt-tiny-2) [Amazon](https://savrn.com/model-publishers/amazon) Update Feb 14, 2025: Chronos-Bolt models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Chronos-Bolt is a family of pretrained time series forecasting models which can be used for zero-shot forecasting. It is based on the T5 encoder-decoder architecture and has been trained on nearly 100 billion time series observations. 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… Open weights apache-2.0 9M parameters chronos-forecasting [View model](https://savrn.com/models/chronos-bolt-tiny-2) Model · Time series forecasting ### [chronos-bolt-mini](https://savrn.com/models/chronos-bolt-mini) [Autogluon](https://savrn.com/model-publishers/autogluon) Update Feb 14, 2025: Chronos-Bolt models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Chronos-Bolt is a family of pretrained time series forecasting models which can be used for zero-shot forecasting. It is based on the T5 encoder-decoder architecture and has been trained on nearly 100 billion time series observations. 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… Open weights apache-2.0 21M parameters [View model](https://savrn.com/models/chronos-bolt-mini) Model · Time series forecasting ### [chronos-t5-tiny](https://savrn.com/models/chronos-t5-tiny) [Amazon](https://savrn.com/model-publishers/amazon) Update Feb 14, 2025: Chronos-Bolt & original Chronos models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Update Nov 27, 2024: We have released Chronos-Bolt models that are more accurate (5% lower error), up to 250 times faster and 20 times more memory-efficient than the original Chronos models of the same size. Check out the new models here. Chronos is a family of pretrained time series forecasting models 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… Open weights apache-2.0 8M parameters chronos-forecasting [View model](https://savrn.com/models/chronos-t5-tiny) Model · Time series forecasting ### [chronos-2-synth](https://savrn.com/models/chronos-2-synth) [Autogluon](https://savrn.com/model-publishers/autogluon) This is a variant of the Chronos-2 model which has only been trained on synthetic univariate and multivariate data. For usage and details on the Chronos-2 model, please refer to https://huggingface.co/autogluon/chronos-2. If you find Chronos-2 useful for your research, please consider citing the associated paper Open weights apache-2.0 119M parameters chronos-forecasting [View model](https://savrn.com/models/chronos-2-synth) Model · Time series forecasting ### [chronos-t5-base](https://savrn.com/models/chronos-t5-base) [Amazon](https://savrn.com/model-publishers/amazon) Update Feb 14, 2025: Chronos-Bolt & original Chronos models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Update Nov 27, 2024: We have released Chronos-Bolt models that are more accurate (5% lower error), up to 250 times faster and 20 times more memory-efficient than the original Chronos models of the same size. Check out the new models here. Chronos is a family of pretrained time series forecasting models 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… Open weights apache-2.0 201M parameters chronos-forecasting [View model](https://savrn.com/models/chronos-t5-base) Model · Time series forecasting ### [Kronos-Tokenizer-2k](https://savrn.com/models/kronos-tokenizer-2k) [ShiYu](https://savrn.com/model-publishers/neoquasar) Kronos is the first open-source foundation model for financial candlesticks (K-lines), trained on data from over 45 global exchanges. It is designed to handle the unique, high-noise characteristics of financial data. Kronos is a family of decoder-only foundation models, pre-trained specifically for the "language" of financial markets—K-line sequences. It leverages a novel two-stage framework: 1. A specialized tokenizer first quantizes continuous, multi-dimensional K-line data (OHLCV) into hierarchical discrete tokens. 2. A large, autoregressive Transformer is then pre-trained on these tokens, enabling it to serve as a unified model for diverse quantitative tasks. The success of large-scale… Open weights mit 4M parameters torch [View model](https://savrn.com/models/kronos-tokenizer-2k) Model · Time series forecasting ### [Kronos-mini](https://savrn.com/models/kronos-mini) [ShiYu](https://savrn.com/model-publishers/neoquasar) Kronos is the first open-source foundation model for financial candlesticks (K-lines), trained on data from over 45 global exchanges. It is designed to handle the unique, high-noise characteristics of financial data. Kronos is a family of decoder-only foundation models, pre-trained specifically for the "language" of financial markets—K-line sequences. It leverages a novel two-stage framework: 1. A specialized tokenizer first quantizes continuous, multi-dimensional K-line data (OHLCV) into hierarchical discrete tokens. 2. A large, autoregressive Transformer is then pre-trained on these tokens, enabling it to serve as a unified model for diverse quantitative tasks. The success of large-scale… Open weights mit 4M parameters [View model](https://savrn.com/models/kronos-mini) Model · Time series forecasting ### [TiRex](https://savrn.com/models/tirex) [NX-AI](https://savrn.com/model-publishers/nx-ai) This repository provides the pre-trained forecasting model TiRex introduced in the paper TiRex is a 35M parameter pre-trained time series forecasting model based on xLSTM. TiRex is a pre-trained model that performs time series forecasting without requiring any training on your data. Simply download and use it. TiRex provides both point estimates and quantile estimates. - State-of-the-art Performance over Long and Short Horizons: TiRex achieves top scores in various time series forecasting benchmarks, see GiftEval and ChronosZS. These benchmark show that TiRex provides great performance for both long and short-term forecasting. A detailed documentation of TiRex can be found here… Open weights other tirex [View model](https://savrn.com/models/tirex) Model · Time series forecasting ### [granite-timeseries-ttm-r2](https://savrn.com/models/granite-timeseries-ttm-r2) [IBM Granite](https://savrn.com/model-publishers/ibm-granite) TinyTimeMixers (TTMs) are compact pre-trained models for Multivariate Time-Series Forecasting, open-sourced by IBM Research. With model sizes starting from 1M params, TTM introduces the notion of the first-ever “tiny” pre-trained models for Time-Series Forecasting. The paper describing TTM was accepted at NeurIPS 24. TTM outperforms other models demanding billions of parameters in several popular zero-shot and few-shot forecasting benchmarks. TTMs are lightweight forecasters, pre-trained on publicly available time series data with various augmentations. TTM provides state-of-the-art zero-shot forecasts and can easily be fine-tuned for multi-variate forecasts with just 5% of the training… Open weights apache-2.0 805,280 parameters granite-tsfm [View model](https://savrn.com/models/granite-timeseries-ttm-r2) Model · Time series forecasting ### [Toto-2.0-4m](https://savrn.com/models/toto-2-0-4m) [Datadog](https://savrn.com/model-publishers/datadog) Toto (Time Series Optimized Transformer for Observability) is a family of time series foundation models for multivariate forecasting developed by Datadog. Toto 2.0 is the current generation, featuring u-μP-scaled transformers ranging from 4m to 2.5B parameters, all trained from a single recipe. Forecast quality improves reliably with parameter count across the family. The family sets a new state of the art on three forecasting benchmarks: BOOM, our observability benchmark; GIFT-Eval, the standard general-purpose benchmark; and the recent contamination-resistant TIME benchmark. Inference code is available on GitHub. For more examples, see the Quick Start notebook and GluonTS integration… Open weights apache-2.0 4M parameters pytorch [View model](https://savrn.com/models/toto-2-0-4m) Model · Time series forecasting ### [chronos-bolt-mini](https://savrn.com/models/chronos-bolt-mini-2) [Amazon](https://savrn.com/model-publishers/amazon) Update Feb 14, 2025: Chronos-Bolt models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Chronos-Bolt is a family of pretrained time series forecasting models which can be used for zero-shot forecasting. It is based on the T5 encoder-decoder architecture and has been trained on nearly 100 billion time series observations. 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… Open weights apache-2.0 21M parameters chronos-forecasting [View model](https://savrn.com/models/chronos-bolt-mini-2) Model · Time series forecasting ### [moirai-2.0-R-small](https://savrn.com/models/moirai-2-0-r-small) [Salesforce AI Research](https://savrn.com/model-publishers/salesforce) Moirai 2.0 is a decoder-only universal time series forecasting transformer model pre-trained on: - Subset of GIFT-Eval Pretrain, and Train datasets (Non-leaking historical context). - Mixup data generated from non-leaking subsets of Chronos Dataset. - Synthetic time series produced via KernelSynth introduced in Chronos paper. - Internal Salesforce operational data. We make significant improvements over the first version of Moirai (please refer to the paper for previous version): - Switched from a distributional loss to a quantile loss formulation. - Moved from single-token to multi-token prediction, improving efficiency and stability. - Added a data filtering mechanism to filter out… Open weights cc-by-nc-4.0 11M parameters [View model](https://savrn.com/models/moirai-2-0-r-small) Model · Time series forecasting ### [Toto-2.0-22m](https://savrn.com/models/toto-2-0-22m) [Datadog](https://savrn.com/model-publishers/datadog) Toto (Time Series Optimized Transformer for Observability) is a family of time series foundation models for multivariate forecasting developed by Datadog. Toto 2.0 is the current generation, featuring u-μP-scaled transformers ranging from 4m to 2.5B parameters, all trained from a single recipe. Forecast quality improves reliably with parameter count across the family. The family sets a new state of the art on three forecasting benchmarks: BOOM, our observability benchmark; GIFT-Eval, the standard general-purpose benchmark; and the recent contamination-resistant TIME benchmark. Inference code is available on GitHub. For more examples, see the Quick Start notebook and GluonTS integration… Open weights apache-2.0 22M parameters pytorch [View model](https://savrn.com/models/toto-2-0-22m) Model · Time series forecasting ### [chronos-t5-large](https://savrn.com/models/chronos-t5-large) [Amazon](https://savrn.com/model-publishers/amazon) Update Feb 14, 2025: Chronos-Bolt & original Chronos models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Update Nov 27, 2024: We have released Chronos-Bolt models that are more accurate (5% lower error), up to 250 times faster and 20 times more memory-efficient than the original Chronos models of the same size. Check out the new models here. Chronos is a family of pretrained time series forecasting models 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… Open weights apache-2.0 709M parameters chronos-forecasting [View model](https://savrn.com/models/chronos-t5-large) Model · Time series forecasting ### [chronos-t5-mini](https://savrn.com/models/chronos-t5-mini) [Autogluon](https://savrn.com/model-publishers/autogluon) Update Feb 14, 2025: Chronos-Bolt & original Chronos models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Update Nov 27, 2024: We have released Chronos-Bolt models that are more accurate (5% lower error), up to 250 times faster and 20 times more memory-efficient than the original Chronos models of the same size. Check out the new models here. Chronos is a family of pretrained time series forecasting models 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… Open weights apache-2.0 20M parameters transformers [View model](https://savrn.com/models/chronos-t5-mini) Model · Time series forecasting ### [timesfm-2.0-500m-pytorch](https://savrn.com/models/timesfm-2-0-500m-pytorch) [Google](https://savrn.com/model-publishers/google) TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting. This is not an officially supported Google product. timesfm-2.0-500m is the second open model checkpoint: - It performs univariate time series forecasting for context lengths up to 2048 time points and any horizon lengths, with an optional frequency indicator. Note that it can go even beyond 2048 context even though it was trained with that as the maximum context. - It focuses on point forecasts. We experimentally offer 10 quantile heads but they have not been calibrated after pretraining. - It ideally requires the context to be contiguous (i.e. no… Open weights apache-2.0 499M parameters timesfm [View model](https://savrn.com/models/timesfm-2-0-500m-pytorch) Model · Time series forecasting ### [flowstate](https://savrn.com/models/flowstate) [IBM Research](https://savrn.com/model-publishers/ibm-research) FlowState is the first time-scale adjustable Time Series Foundation Model (TSFM), open-sourced by IBM Research. Combining an State Space Model (SSM) Encoder with a Functional Basis Decoder allows FlowState to transition into a timescale invariant coefficient space and make a continuous forecast from this space. This allows FlowState to seamlessly adjust to all possible sampling rates. Therefore, training in one time-scale helps for inference at all scales, allowing for drastically improved utilization of training data across time-scales. This innovation leads to a significant improvement in performance, making FlowState the new state-of-the art in zero-shot time series forecasting.… Open weights apache-2.0 9M parameters [View model](https://savrn.com/models/flowstate) Model · Time series forecasting ### [Toto-Open-Base-1.0](https://savrn.com/models/toto-open-base-1-0) [Datadog](https://savrn.com/model-publishers/datadog) Toto (Time Series Optimized Transformer for Observability) is a state-of-the-art time-series foundation model designed for multi-variate time series forecasting, emphasizing observability metrics. Toto efficiently handles high-dimensional, sparse, and non-stationary data commonly encountered in observability scenarios. The average rank of Toto compared to the runner-up models on both the GIFT-Eval and BOOM benchmarks (as of May 19, 2025). - Tailored for Observability Metrics with State-of-the-Art Performance on GIFT-Eval and BOOM. Overview of Toto-Open-Base-1.0 architecture. Inference code is available on GitHub. For optimal speed and reduced memory usage, you should also install xFormers… Open weights apache-2.0 151M parameters transformers [View model](https://savrn.com/models/toto-open-base-1-0) Model · Time series forecasting ### [timesfm-2.5-200m-transformers](https://savrn.com/models/timesfm-2-5-200m-transformers) [Google](https://savrn.com/model-publishers/google) TimesFM (Time Series Foundation Model) is a pretrained decoder-only model for time-series forecasting. This repository contains the Transformers port of the official TimesFM 2.5 PyTorch release. This model is converted from the official TimesFM 2.5 PyTorch checkpoint and integrated into transformers as TimesFm25ModelForPrediction. The converted checkpoint preserves the original architecture and forecasting behavior, including: patch-based inputs for time-series contexts decoder-only self-attention stack point and quantile forecasts Weight conversion parity is verified by comparing converted-model forecasts against the official implementation outputs on deterministic inputs. Open weights apache-2.0 231M parameters 16,384 tokens transformers [View model](https://savrn.com/models/timesfm-2-5-200m-transformers) Model · Time series forecasting ### [TimeMoE-50M](https://savrn.com/models/timemoe-50m) [Xiaoming Shi](https://savrn.com/model-publishers/maple728) This repository contains the weights of the TimeMoE-50M model of the paper Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts. For details on how to use this model, please visit our GitHub page. Open weights apache-2.0 113M parameters 4,096 tokens [View model](https://savrn.com/models/timemoe-50m) Model · Time series forecasting ### [granite-timeseries-ttm-r3](https://savrn.com/models/granite-timeseries-ttm-r3) [IBM Granite](https://savrn.com/model-publishers/ibm-granite) Building on top of TTM-R1 and TTM-R2, we introduce the next generation of TinyTimeMixer under the Granite time-series foundation model family — Granite-TTM-R3. This release incorporates several novel tiny-neural architectural innovations designed to push the limits of accuracy in high-speed forecasting, a critical requirement for real-world production deployments. Granite-TTM-R3 is a family of pretrained models supporting multiple real-world forecasting scenarios: - Zero-shot forecasting across unseen datasets - Few-shot adaptation effective with as few as ~1K samples - Full fine-tuning for domain-specific optimization - Multivariate time-series forecasting - Exogenous / control variable… Open weights apache-2.0 1M parameters [View model](https://savrn.com/models/granite-timeseries-ttm-r3) Model · Time series forecasting ### [MOMENT-1-base](https://savrn.com/models/moment-1-base) [Auton Lab](https://savrn.com/model-publishers/autonlab) MOMENT is a family of foundation models for general-purpose time-series analysis. The models in this family (1) serve as a building block for diverse time-series analysis tasks (e.g., forecasting, classification, anomaly detection, and imputation, etc.), (2) are effective out-of-the-box, i.e., with no (or few) task-specific exemplars (enabling e.g., zero-shot forecasting, few-shot classification, etc.), and (3) are tunable using in-distribution and task-specific data to improve performance. For details on MOMENT models, training data, and experimental results, please refer to the paper MOMENT: A Family of Open Time-series Foundation Models. Recommended Python Version: Python 3.11 (support… Open weights mit 113M parameters transformers [View model](https://savrn.com/models/moment-1-base) Model · Time series forecasting ### [moirai-1.1-R-small](https://savrn.com/models/moirai-1-1-r-small) [Salesforce AI Research](https://savrn.com/model-publishers/salesforce) This is new updated version of Moirai-1.0-R (https://huggingface.co/Salesforce/moirai-1.0-R-base). The Moirai-1.1-R model achieved significant improvements (~20%) for low-frequency cases like Yearly and Quarterly data in Normalised Mean Absolute Error (NMAE) for 40 datasets on the Monash repository. This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with… Open weights cc-by-nc-4.0 14M parameters transformers [View model](https://savrn.com/models/moirai-1-1-r-small) Model · Time series forecasting ### [MOMENT-1-small](https://savrn.com/models/moment-1-small) [Auton Lab](https://savrn.com/model-publishers/autonlab) MOMENT is a family of foundation models for general-purpose time-series analysis. The models in this family (1) serve as a building block for diverse time-series analysis tasks (e.g., forecasting, classification, anomaly detection, and imputation, etc.), (2) are effective out-of-the-box, i.e., with no (or few) task-specific exemplars (enabling e.g., zero-shot forecasting, few-shot classification, etc.), and (3) are tunable using in-distribution and task-specific data to improve performance. For details on MOMENT models, training data, and experimental results, please refer to the paper MOMENT: A Family of Open Time-series Foundation Models. Recommended Python Version: Python 3.11 (support… Open weights mit 38M parameters transformers [View model](https://savrn.com/models/moment-1-small) Model · Time series forecasting ### [granite-timeseries-patchtst-fm-r1](https://savrn.com/models/granite-timeseries-patchtst-fm-r1) [IBM Granite](https://savrn.com/model-publishers/ibm-granite) PatchTST was originally released prior to the interest in creating pre-trained, zero-shot time series foundation models that were capable of state-of-the-art performance on out of sample datasets. PatchTST-FM (patched time-series transformer-based foundation model) essentially has the architectural simplicity of PatchTST, but differs in some crucial ways. Coupled with a revised training strategy and a significantly larger training corpus, we are able to train a model that achieves state-of-the-art results on GiftEval (see below for recommended filters to view this on the leaderboard). The architecture incorporates the following changes: - residual blocks in the input and output projections… Open weights apache-2.0 258M parameters [View model](https://savrn.com/models/granite-timeseries-patchtst-fm-r1) Model · Time series forecasting ### [MOMENT-1-large](https://savrn.com/models/moment-1-large) [Auton Lab](https://savrn.com/model-publishers/autonlab) MOMENT is a family of foundation models for general-purpose time-series analysis. The models in this family (1) serve as a building block for diverse time-series analysis tasks (e.g., forecasting, classification, anomaly detection, and imputation, etc.), (2) are effective out-of-the-box, i.e., with no (or few) task-specific exemplars (enabling e.g., zero-shot forecasting, few-shot classification, etc.), and (3) are tunable using in-distribution and task-specific data to improve performance. For details on MOMENT models, training data, and experimental results, please refer to the paper MOMENT: A Family of Open Time-series Foundation Models. Recommended Python Version: Python 3.11 (support… Open weights mit 346M parameters transformers [View model](https://savrn.com/models/moment-1-large) Model · Time series forecasting ### [patchtst-fm-r1](https://savrn.com/models/patchtst-fm-r1) [IBM Research](https://savrn.com/model-publishers/ibm-research) This model card is for the non-commercial, research version of PatchTST-FM-r1. Please also check-out the Apache-2.0 licensed IBM Granite version. PatchTST was originally released prior to the interest in creating pre-trained, zero-shot time series foundation models that were capable of state-of-the-art performance on out of sample datasets. PatchTST-FM (patched time-series transformer-based foundation model) essentially has the architectural simplicity of PatchTST, but differs in some crucial ways. Coupled with a revised training strategy and a significantly larger training corpus, we are able to train a model that achieves state-of-the-art results on GiftEval. The architecture incorporates… Open weights cc-by-nc-sa-4.0 258M parameters [View model](https://savrn.com/models/patchtst-fm-r1) Model · Time series forecasting ### [t0-alpha](https://savrn.com/models/t0-alpha) [The Forecasting Company](https://savrn.com/model-publishers/theforecastingcompany) t0-alpha is an open-weights time-series forecasting foundation model from The Forecasting Company. t0 is a transformer-based model that produces probabilistic multi-horizon forecasts and natively operates on multiple covariates. t0-alpha is the first public iteration of the model. You can use t0 on Retrocast, The Forecasting Company's platform for forecasting on your own data and comparing forecasts across open-weight models. Model family: t0-alpha (PyTorch/MLX) · French national electricity demand in Retrocast. Data: Enedis open data. t0-alpha is an alpha release intended for research, experimentation, and applied forecasting evaluation. t0-alpha is intended for probabilistic time-series… Open weights apache-2.0 102M parameters tfc-t0 [View model](https://savrn.com/models/t0-alpha) Model · Time series forecasting ### [granite-timeseries-patchtst-fm-r2](https://savrn.com/models/granite-timeseries-patchtst-fm-r2) [IBM Granite](https://savrn.com/model-publishers/ibm-granite) PatchTST-FM-r2, a state-of-the-art zero-shot time series foundation model, represents a continuation of the well-recognized PatchTST model series, building on the original PatchTST and its zero-shot variant PatchTST-FM-r1. PatchTST-FM-r2 brings architectural enhancements as well as an expanded training base on top of its predecessor PatchTST-FM-r1. As of August 31, 2026 Granite-TimeSeries-PatchTST-FM-r2 is the top performing zero-shot model released under a permissive, commercial-friendly open-source license on the GIFT-Eval benchmark. Granite-TimeSeries-PatchTST-FM-r2 ranks #2 when considering all zero-shot, replicable models (see below for more details). The architectural changes in r2… Open weights openmdw-1.0 385M parameters [View model](https://savrn.com/models/granite-timeseries-patchtst-fm-r2) Model · Time series forecasting ### [sundial-base-128m](https://savrn.com/models/sundial-base-128m) [THUML @ Tsinghua University](https://savrn.com/model-publishers/thuml) News (2025.08) Sundial has been integrated into Apache IoTDB, a native time-series database. News (2025.06) Sundial has been accepted as ICML 2025 Oral (Top 1%). News (2025.05) Get 1st MASE on the GIFT-Eval Benchmark. News (2025.02) Get 1st MSE/MAE zero-shot performance on Time-Series-Library datasets. Sundial is a family of generative time series foundation models. This version is pre-trained on 1 trillion time points with 128M parameters. For more information, please refer to this paper. [[Slides]](https://cloud.tsinghua.edu.cn/f/8d526337afde465e87c9/) [[Poster]](https://cloud.tsinghua.edu.cn/f/cc2a156315e9453f99b3/) [[Intro (CN)]](https://mp.weixin.qq.com/s/y3sc2e2lmW1sqfnoK-ZdDA). The… Open weights apache-2.0 128M parameters 10,000 tokens transformers [View model](https://savrn.com/models/sundial-base-128m) Model · Time series forecasting ### [granite-timeseries-flowstate-r1](https://savrn.com/models/granite-timeseries-flowstate-r1) [IBM Granite](https://savrn.com/model-publishers/ibm-granite) FlowState is the first time-scale adjustable Time Series Foundation Model (TSFM), open-sourced by IBM Research. Combining a State Space Model (SSM) Encoder with a Functional Basis Decoder allows FlowState to transition into a timescale invariant coefficient space and make a continuous forecast from this space. This allows FlowState to seamlessly adjust to all possible sampling rates. Therefore, training in one time-scale helps for inference at all scales, allowing for drastically improved utilization of training data across time-scales. This innovation leads to a significant improvement in performance, making FlowState the new state-of-the art in zero-shot time series forecasting.… Open weights apache-2.0 9M parameters [View model](https://savrn.com/models/granite-timeseries-flowstate-r1) Model · Time series forecasting ### [Toto-2.0-313m](https://savrn.com/models/toto-2-0-313m) [Datadog](https://savrn.com/model-publishers/datadog) Toto (Time Series Optimized Transformer for Observability) is a family of time series foundation models for multivariate forecasting developed by Datadog. Toto 2.0 is the current generation, featuring u-μP-scaled transformers ranging from 4m to 2.5B parameters, all trained from a single recipe. Forecast quality improves reliably with parameter count across the family. The family sets a new state of the art on three forecasting benchmarks: BOOM, our observability benchmark; GIFT-Eval, the standard general-purpose benchmark; and the recent contamination-resistant TIME benchmark. Inference code is available on GitHub. For more examples, see the Quick Start notebook and GluonTS integration… Open weights apache-2.0 313M parameters pytorch [View model](https://savrn.com/models/toto-2-0-313m) Model · Time series forecasting ### [granite-timeseries-ttm-r1](https://savrn.com/models/granite-timeseries-ttm-r1) [IBM Granite](https://savrn.com/model-publishers/ibm-granite) TinyTimeMixers (TTMs) are compact pre-trained models for Multivariate Time-Series Forecasting, open-sourced by IBM Research. With less than 1 Million parameters, TTM (accepted in NeurIPS 24) introduces the notion of the first-ever “tiny” pre-trained models for Time-Series Forecasting. TTM outperforms several popular benchmarks demanding billions of parameters in zero-shot and few-shot forecasting. TTMs are lightweight forecasters, pre-trained on publicly available time series data with various augmentations. TTM provides state-of-the-art zero-shot forecasts and can easily be fine-tuned for multi-variate forecasts with just 5% of the training data to be competitive. Refer to our paper for… Open weights apache-2.0 805,280 parameters granite-tsfm [View model](https://savrn.com/models/granite-timeseries-ttm-r1) Model · Time series forecasting ### [granite-timeseries-patchtst](https://savrn.com/models/granite-timeseries-patchtst) [IBM Granite](https://savrn.com/model-publishers/ibm-granite) PatchTST is a transformer-based model for time series modeling tasks, including forecasting, regression, and classification. This repository contains a pre-trained PatchTST model encompassing all seven channels of the ETTh1 dataset. This particular pre-trained model produces a Mean Squared Error (MSE) of 0.3881 on the test split of the ETTh1 dataset when forecasting 96 hours into the future with a historical data window of 512 hours. For training and evaluating a PatchTST model, you can refer to this demo notebook. The PatchTST model was proposed in A Time Series is Worth 64 Words: Long-term Forecasting with Transformers by Yuqi Nie, Nam H. Nguyen, Phanwadee Sinthong, Jayant Kalagnanam. At… Open weights apache-2.0 616,032 parameters transformers [View model](https://savrn.com/models/granite-timeseries-patchtst) Model · Time series forecasting ### [moirai-1.0-R-small](https://savrn.com/models/moirai-1-0-r-small) [Salesforce AI Research](https://savrn.com/model-publishers/salesforce) Moirai, the Masked Encoder-based Universal Time Series Forecasting Transformer is a Large Time Series Model pre-trained on LOTSA data. For more details on the Moirai architecture, training, and results, please refer to the paper. Fig. 1: Overall architecture of Moirai. Visualized is a 3-variate time series, where variates 0 and 1 are target variables (i.e. to be forecasted, and variate 2 is a dynamic covariate (values in forecast horizon known). Based on a patch size of 64, each variate is patchified into 3 tokens. The patch embeddings along with sequence and variate id are fed into the Transformer. The shaded patches represent the forecast horizon to be forecasted, whose corresponding… Open weights cc-by-nc-4.0 14M parameters transformers [View model](https://savrn.com/models/moirai-1-0-r-small) Model · Time series forecasting ### [moirai-1.1-R-large](https://savrn.com/models/moirai-1-1-r-large) [Salesforce AI Research](https://savrn.com/model-publishers/salesforce) This is new updated version of Moirai-1.0-R (https://huggingface.co/Salesforce/moirai-1.0-R-large). The Moirai-1.1-R model achieved significant improvements (~20%) for low-frequency cases like Yearly and Quarterly data in Normalised Mean Absolute Error (NMAE) for 40 datasets on the Monash repository. This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with… Open weights cc-by-nc-4.0 311M parameters transformers [View model](https://savrn.com/models/moirai-1-1-r-large) Model · Time series forecasting ### [moirai-1.0-R-large](https://savrn.com/models/moirai-1-0-r-large) [Salesforce AI Research](https://savrn.com/model-publishers/salesforce) Moirai, the Masked Encoder-based Universal Time Series Forecasting Transformer is a Large Time Series Model pre-trained on LOTSA data. For more details on the Moirai architecture, training, and results, please refer to the paper. Fig. 1: Overall architecture of Moirai. Visualized is a 3-variate time series, where variates 0 and 1 are target variables (i.e. to be forecasted, and variate 2 is a dynamic covariate (values in forecast horizon known). Based on a patch size of 64, each variate is patchified into 3 tokens. The patch embeddings along with sequence and variate id are fed into the Transformer. The shaded patches represent the forecast horizon to be forecasted, whose corresponding… Open weights cc-by-nc-4.0 311M parameters transformers [View model](https://savrn.com/models/moirai-1-0-r-large) Model · Time series forecasting ### [moirai-1.1-R-base](https://savrn.com/models/moirai-1-1-r-base) [Salesforce AI Research](https://savrn.com/model-publishers/salesforce) This is new updated version of Moirai-1.0-R (https://huggingface.co/Salesforce/moirai-1.0-R-base). The new Moirai model achieved significant improvements (~20%) for low-frequency cases like Yearly and Quarterly data in Normalised Mean Absolute Error (NMAE) for 40 datasets on the Monash repository. This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with… Open weights cc-by-nc-4.0 91M parameters transformers [View model](https://savrn.com/models/moirai-1-1-r-base) Model · Time series forecasting ### [moirai-moe-1.0-R-base](https://savrn.com/models/moirai-moe-1-0-r-base) [Salesforce AI Research](https://savrn.com/model-publishers/salesforce) This model has been pushed to the Hub using the PytorchModelHubMixin integration: This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people’s lives, rights, or safety. For further guidance on use… Open weights cc-by-nc-4.0 935M parameters [View model](https://savrn.com/models/moirai-moe-1-0-r-base) Model · Time series forecasting ### [moirai-moe-1.0-R-small](https://savrn.com/models/moirai-moe-1-0-r-small) [Salesforce AI Research](https://savrn.com/model-publishers/salesforce) This model has been pushed to the Hub using the PytorchModelHubMixin integration: This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people’s lives, rights, or safety. For further guidance on use… Open weights cc-by-nc-4.0 117M parameters [View model](https://savrn.com/models/moirai-moe-1-0-r-small) Model · Time series forecasting ### [Aurora](https://savrn.com/models/aurora) [DI DaSE ECNU](https://savrn.com/model-publishers/decisionintelligence) alt="Aurora Logo" src="https://cdn-uploads.huggingface.co/production/uploads/66276727368ec2a0b933772c/ytpsIAr98keUvNouoOVmb.png" width="30%" The official code repo of our ICLR 2026 paper: Aurora: Towards Universal Generative Multimodal Time Series Forecasting alt="ICLR 2026" src="https://img.shields.io/badge/ICLR%202026-Aurora-orange" alt="Python" src="https://img.shields.io/badge/Python-3.10%2B-blue" alt="PyTorch" src="https://img.shields.io/badge/PyTorch-2.4.1-blue" alt="GitHub Stars" src="https://img.shields.io/github/stars/decisionintelligence/Aurora?logo=github" alt="GitHub" src="https://img.shields.io/badge/GitHub-Aurora-black?logo=github" Aurora is a highly capable multimodal time… Open weights mit 211M parameters 10,000 tokens [View model](https://savrn.com/models/aurora) Model · Time series forecasting ### [chronos-t5-mini](https://savrn.com/models/chronos-t5-mini-2) [Amazon](https://savrn.com/model-publishers/amazon) Update Feb 14, 2025: Chronos-Bolt & original Chronos models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Update Nov 27, 2024: We have released Chronos-Bolt models that are more accurate (5% lower error), up to 250 times faster and 20 times more memory-efficient than the original Chronos models of the same size. Check out the new models here. Chronos is a family of pretrained time series forecasting models 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… Open weights apache-2.0 20M parameters chronos-forecasting [View model](https://savrn.com/models/chronos-t5-mini-2) Model · Time series forecasting ### [chronos-t5-tiny](https://savrn.com/models/chronos-t5-tiny-2) [Autogluon](https://savrn.com/model-publishers/autogluon) Update Feb 14, 2025: Chronos-Bolt & original Chronos models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Update Nov 27, 2024: We have released Chronos-Bolt models that are more accurate (5% lower error), up to 250 times faster and 20 times more memory-efficient than the original Chronos models of the same size. Check out the new models here. Chronos is a family of pretrained time series forecasting models 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… Open weights apache-2.0 8M parameters transformers [View model](https://savrn.com/models/chronos-t5-tiny-2) Model · Time series forecasting ### [chronos-t5-base](https://savrn.com/models/chronos-t5-base-2) [Autogluon](https://savrn.com/model-publishers/autogluon) Update Feb 14, 2025: Chronos-Bolt & original Chronos models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Update Nov 27, 2024: We have released Chronos-Bolt models that are more accurate (5% lower error), up to 250 times faster and 20 times more memory-efficient than the original Chronos models of the same size. Check out the new models here. Chronos is a family of pretrained time series forecasting models 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… Open weights apache-2.0 201M parameters transformers [View model](https://savrn.com/models/chronos-t5-base-2) Model · Time series forecasting ### [chronos-t5-small](https://savrn.com/models/chronos-t5-small-2) [Autogluon](https://savrn.com/model-publishers/autogluon) Update Feb 14, 2025: Chronos-Bolt & original Chronos models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Update Nov 27, 2024: We have released Chronos-Bolt models that are more accurate (5% lower error), up to 250 times faster and 20 times more memory-efficient than the original Chronos models of the same size. Check out the new models here. Chronos is a family of pretrained time series forecasting models 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… Open weights apache-2.0 46M parameters transformers [View model](https://savrn.com/models/chronos-t5-small-2) Model · Time series forecasting ### [TiRex-1.1-gifteval](https://savrn.com/models/tirex-1-1-gifteval) [NX-AI](https://savrn.com/model-publishers/nx-ai) The 1.1 release introduces long period normalisation, a method applied solely during inference. This specific version (1.1-gifteval) includes the 1.1 improvements plus the pretraining dataset has been cleaned to remove overlaps with the GIFT-Eval test dataset. TiRex is a time-series foundation model designed for time series forecasting, with the emphasis to provide state-of-the-art forecasts for both short- and long-term forecasting horizon. TiRex is 35M parameter small and is based on the xLSTM architecture allowing fast and performant forecasts. The model is described in the paper TiRex: Zero-Shot Forecasting across Long and Short Horizons with Enhanced In-Context Learning. TiRex performs… Open weights other tirex [View model](https://savrn.com/models/tirex-1-1-gifteval) ## Questions ### Which Time series forecasting models are most downloaded? By monthly downloads reported by the Hugging Face Hub: chronos-2 (14.6M); chronos-2 (12.9M); chronos-bolt-small (6.5M). ## Other Tasks - [Text Generation](https://savrn.com/models/tasks/text-generation) 1548 - [Image and Text to Text](https://savrn.com/models/tasks/image-and-text-to-text) 577 - [Feature Extraction](https://savrn.com/models/tasks/feature-extraction) 398 - [Robotics](https://savrn.com/models/tasks/robotics) 398 - [Text Classification](https://savrn.com/models/tasks/text-classification) 331 - [Text to Image](https://savrn.com/models/tasks/text-to-image) 232 - [Speech Recognition](https://savrn.com/models/tasks/speech-recognition) 187 - [Text to Speech](https://savrn.com/models/tasks/text-to-speech) 145 - [Image Classification](https://savrn.com/models/tasks/image-classification) 139 - [Audio Classification](https://savrn.com/models/tasks/audio-classification) 130 - [Sentence Similarity](https://savrn.com/models/tasks/sentence-similarity) 103 - [Reinforcement Learning](https://savrn.com/models/tasks/reinforcement-learning) 100 [See all](https://savrn.com/models/tasks)