TLDRocket
Sign in

Google

254 summarised stories about Google, each linking back to the original source. Browse all topics →

+ Follow this topic

Monday, 31 August 2026

Google AI Releases TimesFM-3: A 330M Parameter Zero-Shot Foundation Model For Multivariate Time Series Forecasting

MarkTechPost 1 month ago 18 ● 3 sources

Google Research released TimesFM-3, a 330M-parameter zero-shot foundation model for multivariate time series forecasting that predicts multiple related series in a single forward pass. It was pretrained on 1T+ time points and outputs 9 quantiles per horizon step. The model becomes usable for benchmarking with released code, but its weights are restricted to non-commercial, non-production use so it can’t be shipped behind a production forecasting API.

Google’s new forecasting model beats everyone. You can’t use it at work (yet).

The New Stack 1 month ago 35 ● 3 sources

Google launched TimesFM-3, a 330-million-parameter forecasting model for multivariate time-series prediction. It was trained on over 1 trillion real-world and synthetic time points and released on Hugging Face under a non-commercial license. As a result, it can be used for non-commercial, non-production work while commercial access will require paid routes, such as when BitQuery swaps to it for its AI.FORECAST command.

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.