mistralai/timestral
Repository for Timestral, the time-series foundation model by Mistral AI
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
Blog post · Hugging Face collection · License Timestral is a family of time series foundation models for multivariate probabilistic forecasting, with support for past-only and known-future covariates. This repository provides standalone inference for Timestral models. It needs only PyTorch, NumPy, safetensors and huggingfacehub, and runs on CPU or GPU. At launch, Timestral-209M ranked first among pretrained and zero-shot models on the three main public forecasting benchmarks: All four sizes (5M, 28M, 123M, 209M) sit on the Pareto front of accuracy versus model size. Full results are in the blog post and the model cards on Hugging Face. Or from a clone with uv, using the versions pinned in uv.lock: The weights are on the Hugging Face Hub, in the Mistral AI organization: frompretrained downloads config.json and model.safetensors once to the Hub cache. as a NumPy array or a torch tensor. The variates of a series are forecast jointly. block;…
Read the full README ↗ · Preview checked 2026-10-27T11:32:25.321Z
Inside the original README — Document outline
- Timestral
- Highlights
- Install
- Models
- Forecast
- Loading options
- Covariates
- Categorical covariates
- Architecture
- Benchmarks
- Contributing
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Repository for Timestral, the time-series foundation model by Mistral AI
Repository facts
- Owner
- mistralai
- Primary language
- Python
- Stars
- 745
- Forks
- 56
- Open issues + pull requests
- 5
- License
- Apache-2.0
- Archived
- No
- Default branch
- main
- Created
- 2026-10-15T10:20:18.000Z
- Last push
- 2026-10-15T14:59:57.000Z
Topics and intended use
No topics were included in the latest source metadata.
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-22T12:12:53.932Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer