# chronos-bolt-base by Amazon: Open-Weight Model Source: https://savrn.com/models/chronos-bolt-base-2 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve chronos-bolt-base (205M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.4 GB | 0.5 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.2 GB | 0.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 23, 2026. [chronos-bolt-base on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/chronos-bolt-base-2/gpus) ## SAVRN's Notes on chronos-bolt-base Time-series forecasting at 205M parameters is a rounding error next to a modern accelerator: 0.4 GB of weights at 16-bit, 0.5 GB with the working margin, and 0.1 GB at 4-bit. The cheapest setup our Index lists is one MI300X with 192 GB at $1.85 an hour, which is absurd overkill — you batch forecasts on CPU or a spare edge GPU, not a datacenter card. Chronos-Bolt is Amazon's T5-style forecaster (vocabulary of two tokens), and the publisher now ships it on SageMaker JumpStart if you would rather not host it yourself. Apache 2.0 covers commercial use, modification and redistribution, with the usual notice, state-changes and patent-grant conditions. The family runs from this base Bolt up through larger Bolts and the earlier chronos-t5 line; base is the pick when you need zero-shot point forecasts without tuning. Weights publish stored as float32 safetensors. At 1.1M downloads a month it is among the most-pulled forecasting checkpoints on the Index, sitting next to Aurora and TimeFM. SAVRN Research ## Model Card By Amazon, published under apache-2.0, revision 5d9f166d69f4. Update Feb 14, 2025: Chronos-Bolt models are now available on Amazon SageMaker JumpStart! Check out the [tutorial notebook](https://github.com/amazon-science/chronos-forecasting/blob/main/notebooks/deploy-chronos-to-amazon-sagemaker.ipynb) 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](https://savrn.com/papers/exploring-the-limits-of-transfer-learning-with-a-unified-text-to-text-transformer) 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 direct multi-step forecasting. Chronos-Bolt models are up to 250 times faster and 20 times more memory-efficient than the [original Chronos](https://savrn.com/papers/chronos-learning-the-language-of-time-series) models of the same size. ### Performance [Read the full model card (835 words)](https://savrn.com/models/chronos-bolt-base-2/card) ## Configuration Architecture ChronosBoltModelForForecasting Vocabulary size 2 Stored precision float32 Model type t5 ## Identity and Version Repository amazon/chronos-bolt-base Publisher Amazon Task Time series forecasting Modality Time series Library chronos-forecasting Parameters 205M parameters Languages Not stated by the source Revision 5d9f166d69f47aef3401367a7b842e78fe97b121 First published 2024-11-25 Last updated 2025-11-21 ## Files and Weights 4 files, 821.2 MB in total. The weights are 1 file totalling 821.2 MB in safetensors. Weights1 file · 821.2 MB Configuration1 file · 1.1 KB Documentation1 file · 8.7 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 821.2 MB | 31f875483a32 | | config.json | Configuration | 1.1 KB | — | | README.md | Documentation | 8.7 KB | — | | .gitattributes | Repository | 1.5 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 821.2 MB [Download from Amazon](https://huggingface.co/amazon/chronos-bolt-base) Released by Amazon through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by [arXiv:1910.10683](https://savrn.com/papers/exploring-the-limits-of-transfer-learning-with-a-unified-text-to-text-transformer) - Described by [arXiv:2403.07815](https://savrn.com/papers/chronos-learning-the-language-of-time-series) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 821.2 MB | | 16-bit | 0.4 GB | | 8-bit | 0.2 GB | | 4-bit | 0.1 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About chronos-bolt-base ### How much GPU memory does chronos-bolt-base need? About 0.5 GB at 16-bit and 0.1 GB at 4-bit: the weights (205M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run chronos-bolt-base on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use chronos-bolt-base commercially? Yes. chronos-bolt-base is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ## Similar Models 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 ### [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 ### [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 ### [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 ### [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 ### [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) ## Amazon [All models and datasets](https://savrn.com/model-publishers/amazon) ## Versions - [5d9f166d69f4](https://savrn.com/models/chronos-bolt-base-2/versions/5d9f166d69f4) · current 2026-10-02 ## Explore More - [All time series forecasting models](https://savrn.com/models/tasks/time-series-forecasting) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-19. - [Amazon website](https://github.com/amazon-science) - [Hugging Face record](https://huggingface.co/amazon/chronos-bolt-base) - [How the hub is built](https://savrn.com/model-hub/methodology)