> ## Content Index
> Fetch the complete content index at: https://globalfeed.ai/llms.txt
> Use this file to discover other available public pages before exploring further.

# Google releases TimesFM-3, a 330M-parameter multivariate forecasting model
- URL: https://globalfeed.ai/en/google-releases-timesfm-3-a-330m-parameter-multivariate-forecasting-model/
- Published: 2026-09-01T11:37:48.000Z
- Updated: 2026-09-01T11:37:48.000Z
- Description: Google Research's TimesFM-3 forecasts several related time series in one forward pass, but its weights are limited to non-commercial use.
- Author: GlobalFeed Editor
- Tags: Google, TimesFM, time series, x-GoogleAI, dil-en, denetim-gerekli, video

Google Research has released **TimesFM-3**, a 330 million parameter time series foundation model that forecasts multiple related series in a single forward pass. Every TimesFM checkpoint through 2.5 was univariate: one series, its own history and nothing else.

TimesFM-3 is pretrained natively for multivariate forecasting on more than 1 trillion time points. It accepts multiple targets, past covariates and past-future covariates with no task-specific fine-tuning. Google's example is ice cream sales, where related product sales, foot traffic, weather, promotions and holidays all move the target.

## Architecture

The backbone remains a decoder-only transformer. Contiguous points are grouped into patches of 32 steps and normalized per series so that wildly different scales do not dominate. Past-future covariate tokens use a lookahead trick: the current patch is concatenated with future patches, so the model sees scheduled events before they occur. Tokens then enter a 2D grid and pass through two alternating attention mechanisms.

Earlier versions decoded one patch at a time, adding latency, compute cost and compounding error. TimesFM-3 uses Contiguous Patch Masking, the training-time masking strategy introduced with TiRex. Masked placeholder tokens are appended for the whole horizon while past-future covariates stay visible, and the alternating attention layers fill every masked horizon patch simultaneously. Each target receives 9 quantiles, the 10th through 90th percentile, at every horizon step.

## Results and licensing

Google evaluated the model on GIFT-Eval, fev-bench and the TIME leaderboard against Chronos-2, the Toto 2.0 family and TimesFM-2.5\. According to the company, TimesFM-3 takes the top average rank among pretrained foundation models on all three, for both point and probabilistic metrics: rank 1 overall on fev-bench across 100 real-world tasks, rank 1 overall on TIME across 50 domain datasets and 98 evaluation tasks, and rank 1 among foundation models on GIFT-Eval.

Part of the repository code is Apache-2.0, but the TimesFM 3.0 weights ship under timesfm-non-commercial-license-v1.0 and are restricted to non-commercial, non-production use. You can benchmark it today; you cannot put it behind a production forecast API.

Full details are in the [MarkTechPost report](https://www.marktechpost.com/2026/08/31/google-ai-releases-timesfm-3-a-330m-parameter-zero-shot-foundation-model-for-multivariate-time-series-forecasting/?ref=globalfeed.ai).