ComfyUI is the node-based interface for AI image and video generation. It runs Stable Diffusion, SDXL, FLUX.1, FLUX.2 and video models like Wan and HunyuanVideo. These models need a lot of VRAM, so hosting ComfyUI on a GPU server is the best way to get fast results without a high-end PC.
Table of Contents
How Much VRAM Does ComfyUI Need?
| Model | VRAM (recommended) | GPU |
|---|---|---|
| Stable Diffusion 1.5 | 4–8 GB | RTX 3060 Ti, RTX 4060 |
| SDXL / SD 3.5 | 8–16 GB | RTX A4000, RTX 4090 |
| FLUX.1 [dev] / [schnell] | 12 GB (FP8) – 24 GB | RTX 4090 |
| FLUX.2 [klein] 4B / 9B | 8–13 GB | RTX A4000, RTX 4090 |
| FLUX.2 [dev] 32B | 24 GB (quantized) – 48 GB+ | RTX 4090/5090, RTX A6000 |
| Video models (Wan, HunyuanVideo) | 24–80 GB | RTX 5090, A100, H100 |
Best ComfyUI Hosting Providers
1. RunPod
- Per-second billing in 30+ regions
- Templates: vLLM, ComfyUI, PyTorch, Ollama, Jupyter
- Serverless AI endpoints
- RTX 3090 $0.22/hr · RTX 4090 $0.34/hr · A100 $1.19/hr · H100 $1.99/hr · H200 $3.59/hr (Community Cloud)
Pros
- Very cheap consumer GPUs
- Huge GPU choice up to B200
- Fast start-up
Cons
- Storage billed when stopped
- Community hosts vary
ComfyUI templates with models and custom nodes; RTX 4090 $0.34/hour, RTX 5090 $0.69/hour, and Serverless for ComfyUI APIs.
2. GPU Mart
- Dedicated GPU servers and GPU VPS (US)
- GPUs from P1000 to RTX 5090, RTX PRO 6000, A100 and H100
- One-click AI apps: Ollama, Stable Diffusion, ComfyUI
- GPU VPS from $21/mo · RTX 4090 $409/mo · RTX 5090 from $419/mo · A100 80GB $1,559/mo · H100 $2,099/mo
Pros
- Lowest monthly prices for dedicated GPUs
- Full root/admin access, Windows or Linux
- Multi-GPU servers available
Cons
- Monthly billing only
- US data centers only
One-click ComfyUI on dedicated servers: RTX A4000 VPS $119/month, RTX 4090 $409/month, RTX 5090 from $419/month.
3. HOSTKEY
- GPU servers in the EU, UK and US
- RTX 4090, RTX 5090, RTX PRO 6000, A100, H100
- Pre-installed AI stack: Ollama, Open WebUI, ComfyUI
- GTX 1080 Ti from €70/mo · RTX 4090 €279/mo · RTX 5090 €590/mo · A100 80GB €1,300/mo · H100 €1,590/mo
Pros
- Hourly or monthly billing
- GDPR-friendly EU hosting
- Big-VRAM options
Cons
- Popular GPUs sell out
- Setup slower than cloud pods
ComfyUI images pre-installed; RTX 4090 €279/month, RTX 5090 €590/month.
4. Vast.ai
- GPU marketplace, 68+ GPU types
- On-demand, interruptible and reserved pricing
- Docker templates for AI tools
- Market pricing: RTX 4090 from ~$0.30/hr · A100 80GB from ~$0.43/hr · interruptible 50%+ cheaper
Pros
- Often the lowest prices
- Per-second billing
- Great for experiments
Cons
- Host quality varies
- Not for strict compliance
ComfyUI templates on marketplace RTX 4090s around $0.30/hour.
How to Install ComfyUI on a GPU Server
git clone https://github.com/comfyanonymous/ComfyUI
cd ComfyUI && python3 -m venv venv && source venv/bin/activate
pip install torch torchvision torchaudio
pip install -r requirements.txt
python main.py --listen 0.0.0.0 --port 8188Put ComfyUI behind a password-protected reverse proxy or SSH tunnel, because it has no built-in login. See also our ComfyUI install guide and ComfyUI vs Automatic1111.
FAQ
The RTX 4090 (24 GB) is the best value; the RTX 5090 (32 GB) is faster and handles FLUX.2 and video models better.
Yes. FLUX.2 [klein] runs on 8–13 GB; FLUX.2 [dev] needs 24 GB with quantization or more VRAM at full precision.
Conclusion
For ComfyUI by the hour, RunPod is our pick; for an always-on ComfyUI server, choose GPU Mart or HOSTKEY.
Prices were checked in September 2026 and change often. Always confirm current pricing on the provider’s website before you order.