---
type: "post"
id: "mistral-released-timestral-its-first-time-series-foundation-e44ba8"
slug: "mistral-released-timestral-its-first-time-series-foundation-e44ba8"
title: "Mistral released Timestral , its first time-series foundation model family in 5M, 28M, 123M, and 209M sizes."
description: "Mistral AI has released Timestral, a family of time-series foundation models for zero-shot forecasting."
retrieval_nugget: "Mistral AI has released Timestral, a family of time-series foundation models for zero-shot forecasting."
published_at: "2026-10-23"
updated_at: "2026-10-23"
record_date: "2026-10-23"
date_kind: "published_at"
topics: ["models"]
entities: ["Mistral AI","Timestral","Timestral-209M","Hugging Face","PyTorch"]
related_patterns: []
novelty_label: "same_event"
what_changed: "Same event as Timestral: Mistral's time-series foundation models"
prior_refs: ["memory:374a02f5-289b-8a8b-ac2a-e6d9675af05a","memory:04ecfd82-fb4c-8b32-a2ce-5e99fd252317","memory:9400e91a-6bfa-87f9-aeea-72f24037a792","memory:d005089a-1bb2-8ac3-a094-1b992a4f4eff"]
source_url: "https://huggingface.co/mistralai/Timestral-209M"
source_urls: ["https://huggingface.co/mistralai/Timestral-209M"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:mistral-released-timestral-its-first-time-series-foundation-e44ba8"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/mistral-released-timestral-its-first-time-series-foundation-e44ba8/","markdown":"https://newruntime.com/posts/mistral-released-timestral-its-first-time-series-foundation-e44ba8.md","json":"https://newruntime.com/posts/mistral-released-timestral-its-first-time-series-foundation-e44ba8.json"}
---

# Mistral released Timestral , its first time-series foundation model family in 5M, 28M, 123M, and 209M sizes.

## Retrieval answer

Mistral AI has released Timestral, a family of time-series foundation models for zero-shot forecasting.

Mistral AI has released Timestral, a family of time-series foundation models for zero-shot forecasting. The family is available in 5M, 28M, 123M, and 209M parameter versions; the published Hugging Face repository is for the 209M checkpoint.

According to its model card, Timestral supports univariate and multivariate targets, past-only and known-future covariates, and probabilistic forecasts across 21 quantiles. The 209M model accepts up to 32,768 historical time steps and can forecast up to 1,024 steps in one forward pass. Mistral describes it as a 24-layer patch-based transformer with time and variate attention. The repository provides PyTorch usage instructions for CPU or GPU inference.

Mistral reports benchmark results for Timestral-209M on GIFT-Eval, TIME, and fev-bench, including a GIFT-Eval MASE of 0.658 and CRPS of 0.446. Model weights are released under a Modified MIT license; the model card says source code is available in Mistral's GitHub repository. The source does not establish independent reproduction of the benchmark claims, hosted API availability, pricing, or performance on a particular deployment.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Models](https://newruntime.com/topics/models.md): Explore the models topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)