Mistral releases Timestral, a 209M forecasting model family
Original title: Mistral AI Releases Timestral: A 209M Forecasting Model Family That Outperforms Google’s TimesFM-3
The title says the family outperforms Google’s TimesFM-3; the article body was not in the provided text.
MarkTechPost’s title says Mistral AI released Timestral, a 209M forecasting model family, and that it outperforms Google’s TimesFM-3. The supplied page text is a cookie-consent banner and does not describe architecture, benchmarks, availability, or licensing.
Unconfirmed: Performance and release details are title claims only; the article body was not available.
- Timestral is described in the title as a 209M-parameter family.
- The title claims it outperforms Google’s TimesFM-3.
- No release date, weights, or benchmark numbers appear in the body.
- Organizations
- Mistral AIGoogle
From the original article
14 min read at marktechpost.comMistral released Timestral, a time series foundation model family from 5M to 209M parameters. The 209M model leads GIFT-Eval, TIME and fev-bench among zero-shot models and runs on CPU. The post Mistral AI Releases Timestral: A 209M Forecasting Model Family That Outperforms Google’s TimesFM-3 appeared first on MarkTechPost.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.