---
title: timesfm-3.0-pytorch
canonical_url: "https://www.modelscope.cn/models/google/timesfm-3.0-pytorch"
md_url: "https://www.modelscope.cn/models/google/timesfm-3.0-pytorch.md"
repository: google/timesfm-3.0-pytorch
last_updated: 2026-09-03
license: other
parameters: 330.7M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 638
stars: 5
tags:
  - time-series
  - forecasting
  - pretrained
  - pytorch
  - google
---

# timesfm-3.0-pytorch

> timesfm-3.0-pytorch - google 在 ModelScope 开源的模型。TimesFM 3.0 (PyTorch)

google/timesfm-3.0-pytorch 是 ModelScope 魔搭社区上的 330.7M 参数机器学习模型，采用 other 许可。

- **Repository**: google/timesfm-3.0-pytorch
- **License**: other
- **Parameters**: 330.7M
- **Tags**: time-series, forecasting, pretrained, pytorch, google
- **Downloads**: 638
- **Stars**: 5
- **Last updated**: 2026-09-03

Source: https://www.modelscope.cn/models/google/timesfm-3.0-pytorch

---

# 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 for **TimesFM 3.0**.

## License

This model is released under the **[TimesFM Non-Commercial License v1.0](https://huggingface.co/google/timesfm-3.0-pytorch/blob/main/LICENSE)**.

## Model 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)

## Data
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.



## Citation

@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}
}