---
format: "aidr-story-markdown/v1"
id: "6b9ef23c3cd2a4528c6deac0aba466b66822a3db0511fbdbe354da9a8c7f6f93"
canonical_url: "https://aidr.today/6b9ef23c?lang=en"
title: "Google Opens 330M Parameter TimesFM-3, Beating Major Forecasting Benchmarks"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-08-31T21:00:10.000Z"
category: "Models"
topics: ["google","llm","benchmark","forecasting"]
source_urls: ["https://huggingnews.com/ai/google-opens-330m-parameter-timesfm-3-beating-major-forecasting-benchmar-def0448d"]
summary: "Google launched a foundation model capable of accurate multivariate time series forecasting in a single forward pass. The 330M parameter tool, known as TimesFM…"
---

# Google Opens 330M Parameter TimesFM\-3, Beating Major Forecasting Benchmarks

> [Open the canonical story](<https://aidr.today/6b9ef23c?lang=en>)

**Published:** 2026-08-31T21:00:10.000Z
**Category:** Models
**Topics:** google, llm, benchmark, forecasting

## Summary

Google launched a foundation model capable of accurate multivariate time series forecasting in a single forward pass\. The 330M parameter tool, known as TimesFM…

## Sources

- [Story source](<https://huggingnews.com/ai/google-opens-330m-parameter-timesfm-3-beating-major-forecasting-benchmar-def0448d>)