Mistral releases Timestral, a family of time-series foundation models
Announcement mistral.ai
Mistral AI releases Timestral, its first family of time-series foundation models, in four sizes from 5M to 209M parameters. They produce probabilistic, multivariate forecasts and accept past and known-future covariates. Mistral reports that the largest model ranks first among pre-trained zero-shot models on GIFT-Eval, TIME and fev-bench, and that the family runs without a GPU.
Share on LinkedIn, X or Bluesky, or .
Know related work that belongs here? Suggest a link
Something wrong on this page? Tell the editor
More news
All news- ReleasegNucleus AI publishes Parametric CAD Bench v3 for AI agents that author parametric CAD
- ReleaseUniversalAGI releases SUV-PT, an SUV aerodynamics model with 1.1% drag error on DrivAerML
- EventAutoCFD5 uses DrivAerML as the common training set for its AI/ML comparison of road-car surrogates
- ReleaseLuminary's SHIFT-NVH predicts road-induced body vibration from part gauges, material and speed