Mistral AI releases Timestral, a family of time-series foundation models
Original titleIntroducing Timestral
AISummary
Mistral AI releases Timestral, its first family of time-series foundation models, in four sizes from 5M to 209M parameters.
The largest model ranks first on GIFT-Eval, TIME and fev-bench among pre-trained zero-shot models, and the 209M model runs in about 140 ms per forecast on a standard server CPU. Timestral is available on-prem, in a VPC or air-gapped, with fine-tuning through Mistral Forge, under a modified MIT license.
AIWhy it matters
The post names the four model sizes, the benchmarks used, and the CPU latency figures, which help readers judge the accuracy and speed tradeoffs for forecasting workloads.
Source: Mistral AI · mistral.aiPublished · added here