Skip to content

Beta: real launches, updated every morning. Rankings may change while we tune them.

Daily Launch

Timestral 209M

Timestral is a family of time series foundation models for zero-shot forecasting, available in 5M, 28M, 123M, and 209M parameter versions. This repository contains the 209M checkpoint. Timestral supports univariate and multivariate forecasting, past-only and known-future covariates, and probabilistic predictions across 21 quantiles. It accepts up to 32,768 historical time steps and forecasts up to 1,024 steps in a single forward pass.

84Rank on 26 October 2026Down 26 places from 25 Oct

Timestral 209M launched on 14 October 2026. It ranked #84 on Daily Launch on 26 October 2026 with a Launch Score of 26, from trending score 227 on Hugging Face. It moved down 26 places from the day before.

Visit siteTrending on Hugging Face · trending score 227, 376 likes
Share

What is Timestral 209M?

Timestral 209M is a model by mistralai on Hugging Face.

How to get Timestral 209M

pip install git+https://github.com/mistralai/timestral.git

From its model card on Hugging Face

More steps and the source are in its model card on Hugging Face.

Daily Launch card for Timestral 209M

Launch timeline

  1. Hugging FacePublished on Hugging Face

  2. Hugging FaceTrending score 231, ranked #76 on Daily Launch

  3. Hugging FaceTrending score 256, ranked #84 on Daily Launch

  4. Hugging FaceTrending score 237, ranked #100 on Daily Launch

  5. Hugging FaceTrending score 236, ranked #72 on Daily Launch

  6. Hugging FaceTrending score 249, ranked #58 on Daily Launch

  7. Hugging FaceTrending score 227, ranked #84 on Daily Launch

Launch Score, last 7 days

05010020 Oct: 020 Oct21 Oct: 3121 Oct22 Oct: 2622 Oct23 Oct: 2423 Oct24 Oct: 2624 Oct25 Oct: 3325 Oct26 Oct: 2626 Oct26 26 Oct
Launch Score, 0 to 100. Days it was not ranked show 0.

Similar new launches