# Mistral launches Timestral: time-series foundation models

> Mistral's new time-series foundation models forecast with 209M parameters, outperforming benchmarks on CPU.
- Title: Mistral launches Timestral: time-series foundation models
- Summary: Mistral's new time-series foundation models forecast with 209M parameters, outperforming benchmarks on CPU. Mistral released Timestral, a family of…
- Keywords: timestral, mistral, time-series, foundation models, probabilistic forecasts, cpu inference, forecasting, multivariate, technology, startups, launches, foundation
- Source: Mistral — https://mistral.ai/news/timestral
- Read time: 1 min
- Topics: timestral, mistral, time-series, foundation models, probabilistic forecasts, cpu inference, forecasting, multivariate, technology, startups
## Introducing Timestral
Mistral released Timestral, its first family of time-series foundation models delivering probabilistic forecasts with 209M parameters.
## Benchmark Results
Timestral ranks first on GIFT-Eval, TIME, and fev-bench benchmarks with 209M parameters, outperforming previous state of the art.
## Family of Models
Timestral offers four model sizes: 5M, 28M, 123M, and 209M parameters, balancing accuracy and efficiency for different use cases.
## CPU Inference
Timestral runs efficiently on CPUs without GPUs, forecasting one day ahead from three weeks of 15-minute history in 10 ms with the 5M model.
## Industrial Example
Timestral improves industrial sensor forecasts through multivariate, probabilistic, and categorical covariate inputs for better accuracy.
## Key Technical Contributions
Timestral uses decoupled horizon forecasting, covariate-aware attention, synthetic-first data, and two-stage training for better time-series predictions.
## Adaptation Options
Timestral supports zero-shot inference, domain-specific covariates, fine-tuning on proprietary data, and full control over training data.
## What's Next
Mistral will publish a GitHub repository for running Timestral on user data and a technical report with full results.
## Model Specifications
Timestral has 32,768 time steps context length, outputs probabilistic forecasts with 21 quantiles, and runs on-prem or air-gapped environments.
## Why Timestral Matters
Timestral enables better forecasting for industrial plants, finance teams, and other enterprises by handling multivariate data and known future covariates.
## Next Steps
Mistral will release a technical report and GitHub repository for Timestral, allowing users to run the models on their own data.
## Key takeaway

Mistral released Timestral, a family of time-series foundation models that deliver probabilistic forecasts with 5M, 209M parameters, running efficiently on CPUs.