google/timesfm-3.0-pytorch
Summary
TimesFM 3.0 is a pretrained time-series foundation model by Google Research, released on Hugging Face with PyTorch weights for time-series forecasting tasks.
View Cached Full Text
Cached at: 09/01/26, 05:46 PM
google/timesfm-3.0-pytorch · Hugging Face
Source: https://huggingface.co/google/timesfm-3.0-pytorch TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
This repository contains the official PyTorch weights and configurations forTimesFM 3.0.
https://huggingface.co/google/timesfm-3.0-pytorch#licenseLicense
This model is released under the**TimesFM Non-Commercial License v1.0**.
https://huggingface.co/google/timesfm-3.0-pytorch#model-detailsModel Details
- Architecture: Stacked Mixing Transformer with Variate Attention and CPM Iterative RevIN.
- Context Patch Length: 32
- Forecast Horizon Patch Length: 64
- Layers: 20 transformer layers (model dim: 1280, heads: 16)
- Quantiles: (median at index 4)
https://huggingface.co/google/timesfm-3.0-pytorch#dataData
timesfm-3.0 is pretrained using
- GiftEvalPretrain excluding the datasets that overlap with fev-bench
- Wikipedia Pageviews, cutoff Nov 2023 (see paper for details).
- Google Trends top queries, cutoff EoY 2022 (see paper for details).
- Synthetic and augmented data.
https://huggingface.co/google/timesfm-3.0-pytorch#citationCitation
@article{das2023decoder, title={A decoder-only foundation model for time-series forecasting}, author={Das, Abhimanyu and Kong, Weihao and Sen, Rajat and Zhou, Yichen}, journal={arXiv preprint arXiv:2310.10688}, year={2023} }
Similar Articles
google-research/timesfm
Google Research releases TimesFM 2.5, an open-source time-series foundation model for forecasting, with 200M parameters, 16k context length, and support for quantile forecasts up to 1k horizon. The model is available on PyPI and Hugging Face, with fine-tuning via LoRA and integration into Google products like BigQuery ML, Google Sheets, and Vertex Model Garden.
TimesFM-3: A zero-shot foundation model for multivariate forecasting
Google introduces TimesFM-3, a state-of-the-art zero-shot foundation model for multivariate time series forecasting, capable of handling multiple targets and covariates in a single forward pass without fine-tuning.
google/tabfm-1.0.0-pytorch
Google Research releases TabFM, a zero-shot tabular foundation model for classification and regression using PyTorch, requiring no fine-tuning.
Zer0Fit: I took Google's new TabFM & TimesFM ML foundation models and made them available as an MCP server for zero-shot ML tasks (forecasts / classifications / regressions). 100% local. [P]
Zer0Fit provides an MCP server that wraps Google's TabFM and TimesFM foundation models for zero-shot forecasting, classification, and regression tasks, running entirely locally.
@oragnes: Google quietly open-sourced the time-series forecasting base model TimesFM 2.5—params down to 200 M, context up to 16 k. Feed it raw history and get instant zero-shot forecasts; perfect for crypto predictions, fam 😂
Google open-sourced TimesFM 2.5, a 200 M-parameter, 16 k-context zero-shot time-series forecasting base model that works straight out of the box on historical data.