Skip to content

[ZeroGPU] xlarge size #2178

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
cbensimon merged 4 commits into from
Jan 29, 2026
Merged

[ZeroGPU] xlarge size #2178

Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b5894f2
[ZeroGPU] `xlarge` size
cbensimon Jan 22, 2026
248a470
Clarify quota consumption details for xlarge instances
cbensimon Jan 22, 2026
915e3b9
durations -> duration
cbensimon Jan 22, 2026
97d336a
Update note on xlarge queueing behavior
cbensimon Jan 27, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 26 additions & 2 deletions docs/hub/spaces-zerogpu.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,15 @@ Unlike traditional single-GPU allocations, ZeroGPU's efficient system lowers bar

## Technical Specifications

- **GPU Type**: Nvidia H200 slice
- **Available VRAM**: 70GB per workload
ZeroGPU supports two GPU sizes

| GPU size | Backing hardware | Vram | Quota cost |
|---------------------|------------------|--------------------------|------------|
| `large` *(default)* | Half NVIDIA H200 | 70GB | 1× |
| `xlarge` | Full NVIDIA H200 | 141GB | 2× |

> [!NOTE]
> See [GPU size selection](#gpu-size-selection) to learn how to use sizes

## Compatibility

Expand Down Expand Up @@ -87,6 +94,23 @@ gr.Interface(

Note: The `@spaces.GPU` decorator is designed to be effect-free in non-ZeroGPU environments, ensuring compatibility across different setups.

## GPU size selection

The default size used by `@spaces.GPU` is `large` (half H200).

You can explicitly request a full H200 by specifying `size="xlarge"`:

``` python
@spaces.GPU(size="xlarge")
def generate(prompt):
return pipe(prompt).images
```

> [!NOTE]
> - `xlarge` consumes **2×** more daily quota than `large` (e.g. a 45s **effective** task duration consumes 90s of quota)
> - `xlarge` usually means increased queuing probability and duration
> - Only use `xlarge` when your workload truly benefits from the additional compute or memory

## Duration Management

For functions expected to exceed the default 60-second of GPU runtime, you can specify a custom duration:
Expand Down