NV-Reason-CT
NV-Reason-CT is a 3D vision-language model for chest and abdominal CT analysis, combining a native 3D vision encoder with a Qwen3.5-4B language model. It supports report generation, question answering, and reasoning, and is released for research and educational use.
What it does
Radiologists, medical students, and medical researchers can use it to generate reports and explore questions about chest and abdominal CT scans for research and educational purposes.
- Availability
- Hugging Face model repository and Gradio web demo
- Pricing model
- Not established
- Deployment
- Python, PyTorch, and Transformers; CUDA-capable GPU recommended
- Privacy
- Not established
- Licence
- OpenMDW-1.1 License
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- The model is designed for radiology report generation, question answering, and multi-step reasoning across chest and abdominal CT volumes. [1]
designed for radiology report generation, general question answering, and
NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights. - It accepts 3D NIfTI CT volumes and natural-language text prompts. [1]
- The model is available from the NVIDIA Hugging Face repository, with a Gradio web demo linked. [1]
- The model can be loaded with Transformers and run on a CUDA device. [1]
The same loaded model can be reused with other prompts and anatomy regions.
NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights. - Use of the model is governed by the OpenMDW-1.1 License. [1]
Use of this model is governed by the [OpenMDW-1.1 License](https://github.com/OpenMDW/OpenMDW/blob/main/1.1/LICENSE.OpenMDW-1.1).
NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model is intended for research and educational purposes and should not be used for clinical diagnosis or treatment decisions. [1]
This model is designed for research and educational purposes only and should
NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights.
Sources
1
1
Verified
Versions
3| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 3 | 2026-10-09 03:11 UTC | evidence update | score | Current |
| 2 | 2026-09-28 13:05 UTC | material change | modality, deployment | Current |
| 1 | 2026-09-27 14:04 UTC | publication | None | Current |
In briefs
1- Xiaomi MiMo introduces MiMo-V2.6-Flash-MOPD Daily brief 2026-09-27
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.