# ZeroGPU quota error when I logged in
**URL:**
**Author:**  [@Realcat](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FRealcat)%5C
**Post date:** [July 24, 2025, 1:37am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F1 "2025-07-24T01:37:05Z")
I’m encountering a strange issue where I get a “ZeroGPU quota exceeded” error when running apps (both mine and others’) while signed in:
```auto
ZeroGPU quota exceeded
You have exceeded your free GPU quota (60s requested vs. 55s left). Try again in 13:46:29
```
Here is my space:
> **[Image Matching Webui - a Hugging Face Space by Realcat](https://huggingface.co/spaces/Realcat/image-matching-webui)**
>
> This app helps you find matching images based on their visual features. You upload images, and the app identifies similar ones from a dataset. It runs on a server and uses a configuration file to m...
This happens regardless of using `@spaces.GPU(duration=60)`, `@spaces.GPU(duration=120)`, or just `@spaces.GPU`.
However, when I sign out, everything works fine without any quota errors.
Has anyone experienced this? How can I resolve this issue?
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [July 24, 2025, 2:35am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F2 "2025-07-24T02:35:23Z")
from [README.md](https://huggingface.co/spaces/Realcat/image-matching-webui/blob/main/README.md):
```yaml
sdk: gradio
sdk_version: 5.38.0
```
If your version of Gradio is older than `5.12.0`, it may have been a known bug, but it is likely an unknown or new bug or malfunction. @meganariley @hysts
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [July 24, 2025, 2:51am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F3 "2025-07-24T02:51:38Z")
Oh. I just remembered that Spaces behavior can vary depending on browser settings and versions, so trying it once in a different browser will make debugging faster.
---
**Author:**  [@Realcat](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FRealcat)%5C
**Post date:** [July 24, 2025, 3:09am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F4 "2025-07-24T03:09:32Z")
I just tried using chrome in incognito mode, and I’m still experiencing the same issue. When logged in, I get a ‘quota exceeded’ error, but after logging out, the problem disappears.
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [July 24, 2025, 3:10am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F5 "2025-07-24T03:10:41Z")
Thank you. That being the case, it is indeed behavior that I have never seen before (at least I haven’t).
---
**Author:**  [@hysts](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fhysts)%5C
**Post date:** [July 24, 2025, 3:32am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F6 "2025-07-24T03:32:49Z")
I don’t think it’s related to gradio version. (Using the latest version is recommended, though.)
The behavior is expected. Non-logged-in users have quota based on their IP addresses.
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [July 24, 2025, 4:02am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F7 "2025-07-24T04:02:48Z")
Hmm. Thank you, hysts!
---
**Author:**  [@Realcat](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FRealcat)%5C
**Post date:** [July 24, 2025, 4:14am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F8 "2025-07-24T04:14:41Z")
Got it! Thanks @hysts
---
**Author:**  [@jbenbudd](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fjbenbudd)%5C
**Post date:** [July 24, 2025, 6:22am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F9 "2025-07-24T06:22:24Z")
I am currently getting:
> Error
> Unlogged user is runnning out of daily ZeroGPU quotas. Signup for free on [https://huggingface.co/join](https://huggingface.co/join) or login on [Hugging Face – The AI community building the future.](https://huggingface.co/login) to get more ZeroGPU quota now.
and I am logged in as a Pro user.
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [July 24, 2025, 6:43am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F10 "2025-07-24T06:43:51Z")
For which spaces?
---
**Author:**  [@alicecbonafe](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Falicecbonafe)%5C
**Post date:** [August 13, 2025, 10:43am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F11 "2025-08-13T10:43:46Z")
I’m using a private space and getting this error. It’s just a test project, I’m trying to understand how to use ZeroGPU, but I’m logged as a pro user and still getting the free quota error.
Here’s the full stack:
`Traceback (most recent call last): File “/usr/local/lib/python3.10/site-packages/gradio/queueing.py”, line 622, in process_events response = await route_utils.call_process_api( File “/usr/local/lib/python3.10/site-packages/gradio/route_utils.py”, line 323, in call_process_api output = await app.get_blocks().process_api( File “/usr/local/lib/python3.10/site-packages/gradio/blocks.py”, line 2016, in process_api result = await self.call_function( File “/usr/local/lib/python3.10/site-packages/gradio/blocks.py”, line 1567, in call_function prediction = await fn(*processed_input) File “/usr/local/lib/python3.10/site-packages/gradio/utils.py”, line 813, in async_wrapper response = await f(*args, **kwargs) File “/usr/local/lib/python3.10/site-packages/gradio/chat_interface.py”, line 638, in _submit_fn response = await anyio.to_thread.run_sync( File “/usr/local/lib/python3.10/site-packages/anyio/to_thread.py”, line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File “/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py”, line 2476, in run_sync_in_worker_thread return await future File “/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py”, line 967, in run result = context.run(func, *args) File “/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py”, line 183, in gradio_handler schedule_response = client.schedule(task_id=task_id, request=request, duration=duration_) File “/usr/local/lib/python3.10/site-packages/spaces/zero/client.py”, line 168, in schedule raise error(“ZeroGPU quota exceeded”, message, html=True) spaces.zero.gradio.HTMLError: Unlogged user is runnning out of daily ZeroGPU quotas. Signup for free on ``https://huggingface.co/join`` or login on ` [https://huggingface.co/login`](https://huggingface.co/login%60) to get more ZeroGPU quota now.`
And here’s my app.py:
```python
import os
import gradio as gr
# from huggingface_hub import login
import spaces
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "0"
from huggingface_hub import snapshot_download
MODEL_ID = "HuggingFaceH4/zephyr-7b-beta"
snapshot_download(
repo_id=MODEL_ID,
local_dir="model",
local_dir_use_symlinks=False,
token=os.environ["HF_TOKEN"],
max_workers=1
)
tokenizer = AutoTokenizer.from_pretrained("model")
model = AutoModelForCausalLM.from_pretrained("model").to("cuda")
@spaces.GPU
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
request: gr.Request,
):
prompt_parts = [f"System: {system_message}"]
for user_msg, bot_msg in history:
if user_msg:
prompt_parts.append(f"User: {user_msg}")
if bot_msg:
prompt_parts.append(f"Assistant: {bot_msg}")
prompt_parts.append(f"User: {message}")
prompt_text = "\n".join(prompt_parts)
inputs = tokenizer(prompt_text, return_tensors="pt").to("cuda")
outputs = model.generate(
**inputs,
max_new_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
do_sample=True
)
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
if "Assistant:" in generated_text:
generated_text = generated_text.split("Assistant:")[-1].strip()
return generated_text
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
)
if __name__ == " __main__":
demo.launch()
```
Any clues?
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [August 13, 2025, 10:48am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F12 "2025-08-13T10:48:27Z")
If the version of Gradio specified in `README.md` (or perhaps in `requirements.txt`) is` 5.12.0` or later, a new bug is suspected. [If you are using earlier Gradio, there is a known bug](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fissue-with-zerogpu-quota-on-hugging-face-pro-account%2F154576%2F2).
---
**Author:**  [@alicecbonafe](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Falicecbonafe)%5C
**Post date:** [August 13, 2025, 10:52am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F13 "2025-08-13T10:52:26Z")
I’m not specifing Gradio’s version, here’s my README.md:
```markdown
---
title: Zero Test
emoji: 💬
colorFrom: yellow
colorTo: purple
sdk: gradio
sdk_version: 5.0.1
app_file: app.py
pinned: false
---
```
And here is my requirements.txt:
```auto
huggingface_hub==0.25.2
torch
transformers
```
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [August 13, 2025, 10:57am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F14 "2025-08-13T10:57:48Z")
> sdk\_version: 5.0.1
Oh. `sdk_version` is Gradio version in this case. Change this value to `5.12.0` [or later](https://pypi.org/project/gradio/#history).
---
**Author:**  [@alicecbonafe](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Falicecbonafe)%5C
**Post date:** [August 13, 2025, 11:05am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F15 "2025-08-13T11:05:12Z")
It worked, thank you!
---
**Author:**  [@ritoseo](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fritoseo)%5C
**Post date:** [September 7, 2025, 2:11pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F16 "2025-09-07T14:11:58Z")
I tried to test deepseek-ai/deepseek-vl2-small model with login pro account.
And I got an error as ‘Unlogged user is runnning out of daily ZeroGPU quotas. Signup for free on [https://huggingface.co/join](https://huggingface.co/join) or login on [Hugging Face – The AI community building the future.](https://huggingface.co/login) to get more ZeroGPU quota now.’
Current account status is like below.
What should I do for running?
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [September 7, 2025, 8:17pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fzerogpu-quota-error-when-i-logged-in%2F164314%2F17 "2025-09-07T20:17:13Z")
I think it’s the same problem as above. You’ll need to duplicate it and modify these parts.
### [README.md](https://huggingface.co/spaces/deepseek-ai/deepseek-vl2-small/blob/main/README.md):
> sdk\_version: 4.21.0
### [requirements.txt](https://huggingface.co/spaces/deepseek-ai/deepseek-vl2-small/blob/main/requirements.txt):
> gradio==3.48.0
> gradio-client==0.6.1