---
title: "Hugging Face ZeroGPU Free GPU Access on Spaces"
slug: "hugging-face-zerogpu-spaces"
provider: "Hugging Face"
status: "verified"
verifiedAt: "2026-10-12"
listedAt: "2026-09-12"
canonical: "https://aifree.dev/offer/hugging-face-zerogpu-spaces"
---

# Hugging Face ZeroGPU Free GPU Access on Spaces

> ZeroGPU dynamically allocates NVIDIA RTX Pro 6000 Blackwell GPUs to Gradio

- Provider: [Hugging Face](https://aifree.dev/provider/huggingface-co)
- What is free: 5 minutes/day
- Status: verified by a person on 2026-10-12
- Credit card: not required
- Sign-up: not required
- For: Startups
- Regions: worldwide
- Resets: daily
- Claim at: https://huggingface.co/docs/hub/en/spaces-zerogpu

## What you get

ZeroGPU dynamically allocates NVIDIA RTX Pro 6000 Blackwell GPUs (48GB or 96GB slices) to Gradio Spaces on demand. Running existing ZeroGPU Spaces is free for all users (even unauthenticated), and free accounts in good standing can host up to 2 ZeroGPU Spaces.

## The catch

Hosting needs a verified email and a 30+ day account; free users get 5 GPU minutes a day, Gradio only. Outside ZeroGPU, new Gradio or Docker Spaces need PRO.

## Eligibility

Anyone can run ZeroGPU Spaces; hosting requires a free account in good standing.
- Verified email and account older than 30 days to host ZeroGPU Spaces

## Limits

- Free account: 5 minutes/day GPU quota, medium queue priority; resets 24h after first GPU usage
- Unauthenticated visitors: 2 minutes/day, low priority
- PRO 40 min/day; Team member 40 min/day; Enterprise 60 min/day
- Hosting: max 2 ZeroGPU Spaces on free accounts (verified email, account 30+ days old)
- Gradio or Docker Spaces on CPU (not ZeroGPU) need PRO to create or duplicate; Static Spaces are free
- Gradio SDK only; default 60s function runtime (@spaces.GPU(duration=...) to extend)
- xlarge (96GB) GPU size consumes 2x quota
- No torch.compile; PyTorch 2.8+ ahead-of-time compilation supported

## Details

## Overview
[ZeroGPU](https://huggingface.co/docs/hub/en/spaces-zerogpu) is Hugging Face's shared GPU infrastructure for Spaces. Instead of holding a dedicated GPU, a Space requests a GPU slice when a decorated function runs and releases it immediately afterwards. All users can run existing ZeroGPU Spaces for free, and free personal accounts can host their own.

## Free Tier Quotas & Limits
- Free account: 5 minutes of GPU quota per day, medium queue priority
- Unauthenticated visitors: 2 minutes per day
- PRO account: 40 minutes per day with highest priority; Team organization member: 40 minutes; Enterprise: 60 minutes
- Included daily quota resets 24 hours after your first GPU usage
- Default function runtime is 60 seconds; extend with @spaces.GPU(duration=...)
- Hosting: free personal accounts in good standing (verified email, account older than 30 days) can host up to 2 ZeroGPU Spaces
- PRO accounts can host up to 10; Team and Enterprise organizations up to 50
- PRO, Team, and Enterprise users can extend beyond the daily quota with pre-paid credits at $1 per 10 minutes of GPU time

## GPU Hardware
- large (default): half NVIDIA RTX Pro 6000 Blackwell with 48 GB VRAM, 1x quota cost
- xlarge: full NVIDIA RTX Pro 6000 Blackwell with 96 GB VRAM, 2x quota cost

## Requirements
- ZeroGPU Spaces are compatible only with the Gradio SDK (version 4 or newer)
- PyTorch 2.8.0 or later; Python 3.10 or 3.12
- Decorate GPU-dependent functions with @spaces.GPU and place models on CUDA at module level
- torch.compile is not supported; use PyTorch ahead-of-time compilation instead

## How to Get Started
Create a free Hugging Face account, then either use the curated list of existing ZeroGPU Spaces or create a Gradio Space and select ZeroGPU as its hardware.

## More

- HTML page: https://aifree.dev/offer/hugging-face-zerogpu-spaces
- Change history: https://aifree.dev/offer/hugging-face-zerogpu-spaces/history
- How it was verified: https://aifree.dev/offer/hugging-face-zerogpu-spaces/verification
- More in [Free AI coding tools](https://aifree.dev/free-ai-coding-tools.md)
- JSON: https://aifree.dev/api/v1/offers/hugging-face-zerogpu-spaces