OPEN MODELS / Vision language models
Run Inkling-NVFP4 on a cloud GPU
Inkling-NVFP4 is a Vision language models model by thinkingmachines. 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 665 GB for inference with U8 weights, including working memory. Real use depends on resolution, batch size and context length. With 4-bit quantization it needs about 400 GB.
| GPU | Memory | Per hour | 10 hours | |
|---|---|---|---|---|
| 8× RTX PRO 6000 WS | 768 GB | $16.16 | $161.60 | Rent |
| 8× RTX PRO 6000 S | 768 GB | $20.16 | $201.60 | Rent |
| 8× RTX PRO 6000 | 768 GB | $33.68 | $336.80 | Rent |
| 16× A100 | 1280 GB | $42.56 | $425.60 | Rent |
| 8× H200 | 1120 GB | $46.08 | $460.80 | Rent |
Live starting prices from our catalog. You pay per second while the machine runs.
How to run Inkling-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 vllm
vllm serve thinkingmachines/Inkling-NVFP4 --host 0.0.0.0 --port 8000Why run it yourself?
Run document and image understanding on your own GPU: no per-image fee, and files stay on your machine.
Questions
- How much GPU memory does Inkling-NVFP4 need?
- By our estimate about 665 GB for inference (553B parameters). Higher resolution, longer context or bigger batches need more.
- How much does it cost to run Inkling-NVFP4?
- From $16.16 per hour on 8× RTX PRO 6000 WS, billed per second. Ten hours cost about $161.60.
- 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