--- title: README emoji: 🌍 colorFrom: indigo colorTo: indigo sdk: static pinned: false ---
# ZeroGPU Spaces
🚨 This page is out of date: for up-to-date information, see the documentation.
✨ September 2025: checkout this new blogpost about ZeroGPU and compilation.
ZeroGPU is currently in beta:
Please share your feedback about ZeroGPU in the Community tab.
ZeroGPU works great with Dev Mode. Learn more about Dev Mode.
*ZeroGPU* is a new kind of hardware for Spaces. It has two goals : - Provide **free GPU access** for Spaces - Allow Spaces to run on **multiple GPUs** This is achieved by making Spaces efficiently hold and release GPUs as needed (as opposed to a classical GPU Space that holds exactly one GPU at any point in time) ZeroGPU uses _Nvidia H200_ GPU devices under the hood (70GB of vRAM are available for each workload) ## Compatibility *ZeroGPU* Spaces should mostly be compatible with any PyTorch-based GPU Space.
Compatibility with high level HF libraries like `transformers` or `diffusers` is slightly more guaranteed
That said, ZeroGPU Spaces are not as broadly compatible as classical GPU Spaces and you might still encounter unexpected bugs Also, for now, ZeroGPU Spaces only works with the **Gradio SDK** Supported versions: - Gradio: 4+ - PyTorch: `2.1.2` to `2.5.1` (2.3.x is not supported due to a PyToch [bug](https://github.com/pytorch/pytorch/issues/122085)) - Python: `3.10.13` ## Usage In order to make your Space work with ZeroGPU you need to **decorate** the Python functions that actually require a GPU with `@spaces.GPU`
During the time when a decorated function is invoked, the Space will be attributed a GPU, and it will release it upon completion of the function.
Here is a practical example : ```diff +import spaces from diffusers import DiffusionPipeline pipe = DiffusionPipeline.from_pretrained(...) pipe.to('cuda') +@spaces.GPU def generate(prompt): return pipe(prompt).images gr.Interface( fn=generate, inputs=gr.Text(), outputs=gr.Gallery(), ).launch() ``` 1. We first `import spaces` (importing it first might prevent some issues but is not mandatory) 2. Then we decorate the `generate` function by adding a `@spaces.GPU` line before its definition Note that `@spaces.GPU` is effect-free and can be safely used on non-ZeroGPU environments ## Duration If you expect your GPU function to take more than __60s__ then you need to specify a `duration` param in the decorator like: ```python @spaces.GPU(duration=120) def generate(prompt): return pipe(prompt).images ``` It will set the maximum duration of your function call to 120s. You can also specify a duration if you know that your function will take far less than the 60s default. The lower the duration, the higher priority your Space visitors will have in the queue ## Getting Started To **explore and use existing ZeroGPU Spaces**, browse the following list: https://huggingface.co/spaces/enzostvs/zero-gpu-spaces To **create and host your own ZeroGPU Spaces**: - For personal accounts: - Subscribe to PRO. Once subscribed, ZeroGPU will appear in the hardware list on New Space page when you select the Gradio SDK. - For organizations: - Subscribe to the Enterprise Hub. This will enable you to host and collaborate on ZeroGPU Spaces with all your organization members. ## Limitations **Personal accounts** (PRO subscribers) can host up to 10 ZeroGPU Spaces. **Organization accounts** subscribed to the Enterprise Hub can host up to 50 ZeroGPU Spaces.