TimesFM-3

TimesFM-3

Google
Timestral

Timestral

Mistral AI
+
+

Related Products

  • Yeastar P-Series PBX System
    116 Ratings
    Visit Website
  • RaimaDB
    12 Ratings
    Visit Website
  • Kantata
    2,341 Ratings
    Visit Website
  • Gemini Enterprise Agent Platform
    1,161 Ratings
    Visit Website
  • SKU Science
    16 Ratings
    Visit Website
  • InEight
    168 Ratings
    Visit Website
  • OptiSigns
    8,462 Ratings
    Visit Website
  • CompanyCam
    5,585 Ratings
    Visit Website
  • Runn
    37 Ratings
    Visit Website
  • Martus
    187 Ratings
    Visit Website

About

TimesFM-3 is a state-of-the-art time series foundation model designed for highly accurate multivariate forecasting in a single forward pass. The 330 million parameter model is pre-trained on a real-world and synthetic time-series corpus comprising more than 1 trillion time points, building on the efficiency and zero-shot generalization of earlier TimesFM models. It can jointly predict multiple coevolving time series and capture dependencies that improve accuracy without task-specific fine-tuning. The model supports multiple targets with point and quantile forecasts, past covariates that are known only historically, and past-future dynamic covariates such as planned promotions, holidays, or weather forecasts. TimesFM-3 uses a decoder-only transformer architecture, processes contiguous data in patches of 32 time steps, and applies alternating causal temporal attention and full variate attention to combine patterns across time and related series.

About

Timestral is a family of time-series foundation models and a Python inference package for generating multivariate probabilistic forecasts from historical sequences. The four model sizes (5M, 28M, 123M and 209M parameters) support past-only, known-future and categorical covariates, return quantile forecasts, and accept context windows up to 32,768 time steps. Developers can load pretrained weights from the Hugging Face Hub or from local files and run inference on CPU or GPU, then incorporate forecasts into monitoring, capacity-planning, energy, supply-chain, financial-risk, or maintenance workflows. Timestral supports zero-shot forecasting and can be adapted to domain data through Mistral Forge. The package is intended for data scientists, machine-learning engineers, and teams building forecasting systems; repository code is Apache 2.0, while model weights use a separate Modified MIT license.

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Not Supported
On-Premises Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Audience

Data scientists, researchers, and developers wanting to forecast multiple related time series and incorporate historical and known future signals

Audience

Data scientists, machine-learning engineers, forecasting practitioners, and teams developing time-series forecasting systems.

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

API

Offers API Not Supported

API

Offers API Supported

Screenshots and Videos

Screenshots and Videos

No images available

Pricing

No information available.
Free Version Not Supported
Free Trial Not Supported

Pricing

No information available.
Free Version Supported
Free Trial Not Supported

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported

Company Information

Google
Founded: 1998
United States
research.google/blog/timesfm-3-a-zero-shot-foundation-model-for-multivariate-forecasting/

Company Information

Mistral AI
Founded: 2023
France
github.com/mistralai/timestral

Alternatives

Timestral

Timestral

Mistral AI

Alternatives

TimesFM-3

TimesFM-3

Google
CodeQwen

CodeQwen

Alibaba
Kimi K2

Kimi K2

Moonshot AI
Solar Mini

Solar Mini

Upstage AI
Qwen-7B

Qwen-7B

Alibaba
Mistral NeMo

Mistral NeMo

Mistral AI

Categories

AI Models Supported
Foundation Models Supported

Categories

AI Models Supported

Integrations

Mistral Forge Not Supported

Integrations

Mistral Forge Supported
Claim TimesFM-3 and update features and information
Claim TimesFM-3 and update features and information
Claim Timestral and update features and information
Claim Timestral and update features and information