Google releases TimesFM 3.0: 330M parameter zero-shot multivariate forecasting model

osanseviero · x · 2026-09-01

Google Research has released TimesFM 3.0, an open-source foundation model for time series forecasting. With 330 million parameters, it introduces native support for multivariate forecasting in a zero-shot manner, overcoming the univariate limitation of previous versions. Pre-trained on over 1 trillion time points, TimesFM-3 significantly outperforms other models across major benchmarks.

Related event: Google Open-Sources TimesFM 3.0: 330M-Parameter Multivariate Zero-Shot Time Series Foundation Model(11 posts)→

Original post →

More from Models

• OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16
• Argon edges out astra as daily driver, but Claude still wins heavy coding work — iruletheworldmo · 2026-10-16
• NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
• RoboVista benchmark: Gemini-4 Argon hits 81.9% on robotics understanding — berkeley_ai · 2026-10-16
• Dev reports decision model jev beats gpt-6-luna on quality in real training pipeline — genmon · 2026-10-16
• Google won't publish Argon 4 limits in AI Pro—users compare experiences — Consistent-Text-2662 · 2026-10-16

Models channel →