OPEN MODELS / Image editing and upscaling
Run Qwen-Image-Edit-2509-13B-4steps on a cloud GPU
Qwen-Image-Edit-2509-13B-4steps is a Image editing and upscaling model by OPPOer. See how much GPU memory it needs, which GPUs it fits on today and what it costs to run it yourself, billed per second.
GPUs it fits on today
Our estimate is about 34 GB for inference with BF16 weights, including working memory. Real use depends on resolution, batch size and context length.
| GPU | Memory | Per hour | 10 hours | |
|---|---|---|---|---|
| Q RTX 8000 | 45 GB | $0.48 | $4.80 | Rent |
| CMP 170HX | 64 GB | $0.62 | $6.20 | Rent |
| GB10 | 119 GB | $0.71 | $7.10 | Rent |
| A100 SXM4 | 80 GB | $0.72 | $7.20 | Rent |
| RTX A6000 | 48 GB | $0.72 | $7.20 | Rent |
Live starting prices from our catalog. You pay per second while the machine runs.
How to run Qwen-Image-Edit-2509-13B-4steps
- 01
Rent a GPU
Pick one of the GPUs above. Billing is per second; stop the machine and you stop paying.
- 02
Open a terminal or Jupyter
Connect over SSH or open Jupyter in your browser. PyTorch and CUDA are ready to use.
- 03
Download and run the model
Run the commands below. The weights download straight from Hugging Face to your machine.
pip install -U diffusers transformers accelerate
huggingface-cli download OPPOer/Qwen-Image-Edit-2509-13B-4steps --local-dir ./model
python -c "import torch; from diffusers import DiffusionPipeline; p = DiffusionPipeline.from_pretrained('./model', torch_dtype=torch.bfloat16).to('cuda'); print(p)"Why run it yourself?
Batch editing and upscaling are heavy jobs. A cloud GPU finishes them quickly and you stop paying when the job is done.
Questions
- How much GPU memory does Qwen-Image-Edit-2509-13B-4steps need?
- By our estimate about 34 GB for inference (14B parameters). Higher resolution, longer context or bigger batches need more.
- How much does it cost to run Qwen-Image-Edit-2509-13B-4steps?
- From $0.48 per hour on Q RTX 8000, billed per second. Ten hours cost about $4.80.
- Do I need a subscription?
- No. You pay only for the time your machine runs, from your USD balance. Stop it whenever you are done.
Try it on your own GPU in minutes
Pick a GPU, open Jupyter or SSH and run any open model. You pay per second and can stop anytime; no subscription, no setup fee.
- Per-second billing in USD
- PyTorch and CUDA ready in minutes
- Rent from ChatGPT or Claude too