time series
Chronos-2
Amazon (AWS AI) zero-shot forecasting model with covariate in-context learning; report 17 Oct 2025. Context is 8,192 time steps.

Levelmodel
Classtime series
Parameters120M
Context8,192
Released20 Oct 2025
Opennessopen weights permissive
Runs onsingle datacentre GPU, CPU server
Statusactive
Benchmark Results
vendor-reportedindependent
Chronos Benchmark IItime series
Claims SOTA zero-shotvendor-reported
no score in the notes
rank 1
fev-benchtime series
Claims SOTAvendor-reported
no score in the notes
rank 1
GIFT-Evaltime series
zero-shot foundation-model CRPS rank, lower is bettervendor-reported
23.5
02040
Score in mean CRPS rank. Lower is better.
Toto 2.0 report (Datadog)
pretrainedindependentno test-data leakage
0.698
00.71.4
Score in MASE (geo-mean, normalised to Seasonal Naive). Lower is better.
Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations
pretrained; rank is average CRPS rankindependentno test-data leakage
0.485
00.51
Score in CRPS (geo-mean, normalised to Seasonal Naive). Lower is better.
rank 57 of 143, Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations
Claims first among pretrained models, beating TimesFM-2.5 and TiRexvendor-reported
no score in the notes
rank 1
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Lineage
successor
Chronos-Bolt is the parent (successor)high confidencemodel card
Chronos is the parent (successor)high confidencepress claimWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 3 models. Confidence and evidence are the notes' own.
Industry Use Cases
Retail and Logistics
Demand forecastingR&D Topics
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer Encoder-only, T5-encoder-inspired; group attention for cross-series and covariate in-context learning; quantile output; horizon 1,024
- Total parameters
- 120M sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- about 120M
- Context length
- 8,192 tokens
- Input
- time series
- Output
- time series
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- Apache License 2.0 sources
- Access routes
- open weights download, cloud marketplace
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- single datacentre GPU, CPU server
- Footprint
- More than 300 forecasts/s on one A10G
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Links
Developer
Amazonbig tech, USA
Amazonbig tech, USAModel
Chronos-2Amazon, time series
Chronos-2Amazon, time seriesR&D TopicsTime-Series Foundation Models
Use CasesIndustrial Forecasting (Load, Throughput, Demand)IndustrialDemand ForecastingRetail and Logistics
Who Runs Itnone recordedDeployments of these use cases; none names this model.
Use cases 2
Organisations 1
Sources
- amazon/chronos-2 , Hugging Face huggingface.co https://huggingface.co/amazon/chronos-2
- TimesFM vs Chronos vs Moirai: The Leader's Weights Ban Production beri.net https://www.beri.net/article/timesfm-vs-chronos-vs-moirai-time-series-foundation-model-licence-bigquery-sagemaker-cost-2026
- arxiv.org/pdf/2605.20119 https://arxiv.org/pdf/2605.20119
- Introducing Chronos-2: From univariate to universal forecasting amazon.science https://www.amazon.science/blog/introducing-chronos-2-from-univariate-to-universal-forecasting
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Chronos-2", https://aurion.semai.id/models/amazon-chronos-2/, records of October 2026.