Weather and climate

Huawei Pangu-Weather

One of the first weather neural networks, published in Nature and added to ECMWF charts. The weights are open for research only; commercial use is prohibited.

The last open version came out in Jul 2023. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
Huawei Cloud, China
First release
Jan 2023
Latest release
Jul 2023
Sizes
4 models of ~1.1 GB each (1, 3, 6 and 24-hour steps)
License
Non-commercial onlyCC-BY-NC-SA 4.0 — commercial use is explicitly prohibited
Running
On your own serverAlso runs without a GPU
Industries
Science and research, Education
Deploy on your server GitHub

What it does

  • Research weather forecasts a week ahead
  • Comparison with other weather models on your own data
  • Training courses on weather neural networks

Where it is used

Universities and research groupsR&D departments

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Pangu-Weather-lite (описание обучения)
  2. Pangu-Weather (ONNX)

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Huawei Pangu-Weather be used in a commercial project?

No. License: CC-BY-NC-SA 4.0 — commercial use is explicitly prohibited. A commercial product needs a different model or a separate agreement with the rights holder.

What hardware does Huawei Pangu-Weather need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Huawei Pangu-Weather support Russian?

Language does not matter for this model: it does not work with text.

Where can I download Huawei Pangu-Weather and what does it cost?

The Huawei Pangu-Weather weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Weather and climateGoogle DeepMind GraphCast / GenCast / WeatherNext 2Google DeepMind · UKCommercial use allowed

Google DeepMind's family of global weather models: GraphCast (10-day forecast), GenCast (probabilistic ensemble) and WeatherNext 2 with cyclone forecasting. Since August 2026 the weights are cleared for commercial use.

DetailsWeather and climateMicrosoft AuroraMicrosoft Research · USACommercial use allowed

A foundation model of Earth's atmosphere: global weather forecasts, plus separate versions for air quality and ocean waves. Computes a forecast in seconds instead of hours on a supercomputer.

DetailsWeather and climateECMWF AIFSEuropean Centre for Medium-Range Weather Forecasts (ECMWF) · Europe (intergovernmental organization)Commercial use allowed

ECMWF's weather neural network running operationally: a 15-day forecast four times a day, an ensemble version with 51 scenarios, and since version 2, ocean waves.

Details

Source: github.com/198808xc/Pangu-Weather. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.