OPEN MODELS / AI video generation
Run wan2.2-ti2v-5b-nvfp4 on a cloud GPU
wan2.2-ti2v-5b-nvfp4 is a AI video generation model by narendra747. 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 10 GB for inference with U8 weights, including working memory. Real use depends on resolution, batch size and context length.
| GPU | Memory | Per hour | 10 hours | |
|---|---|---|---|---|
| RTX 3060 | 12 GB | $0.14 | $1.40 | Rent |
| Titan Xp | 12 GB | $0.16 | $1.60 | Rent |
| GTX 1080 Ti | 11 GB | $0.17 | $1.70 | Rent |
| GTX TITAN X | 12 GB | $0.17 | $1.70 | Rent |
| RTX 2060 | 12 GB | $0.17 | $1.70 | Rent |
Live starting prices from our catalog. You pay per second while the machine runs.
How to run wan2.2-ti2v-5b-nvfp4
- 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 narendra747/wan2.2-ti2v-5b-nvfp4 --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?
Hosted video tools charge per clip or per month and put you in a queue. On your own GPU you pay only for the time it runs, make as many clips as you like and keep your prompts and files on your machine.
Questions
- How much GPU memory does wan2.2-ti2v-5b-nvfp4 need?
- By our estimate about 10 GB for inference (6.7B parameters). Higher resolution, longer context or bigger batches need more.
- How much does it cost to run wan2.2-ti2v-5b-nvfp4?
- From $0.14 per hour on RTX 3060, billed per second. Ten hours cost about $1.40.
- 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