Instructions to use MBZUAI/MediX-R1-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MBZUAI/MediX-R1-2B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="MBZUAI/MediX-R1-2B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("MBZUAI/MediX-R1-2B")
model = AutoModelForImageTextToText.from_pretrained("MBZUAI/MediX-R1-2B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MBZUAI/MediX-R1-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MBZUAI/MediX-R1-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MBZUAI/MediX-R1-2B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/MBZUAI/MediX-R1-2B

SGLang

How to use MBZUAI/MediX-R1-2B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "MBZUAI/MediX-R1-2B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MBZUAI/MediX-R1-2B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "MBZUAI/MediX-R1-2B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MBZUAI/MediX-R1-2B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use MBZUAI/MediX-R1-2B with Docker Model Runner:
```
docker model run hf.co/MBZUAI/MediX-R1-2B
```

jazeelmohd commited on Feb 27

Commit

c34d95a

verified ·

1 Parent(s): 2e2c449

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -6

README.md CHANGED Viewed

@@ -28,7 +28,7 @@ library_name: transformers
 #### **Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), UAE**
 [![Website](https://img.shields.io/badge/Project-Website-87CEEB)](https://medix.cvmbzuai.com)
-[![Paper](https://img.shields.io/badge/arXiv-Paper-red.svg)](#)
 [![HuggingFace](https://img.shields.io/badge/HuggingFace-Page-F9D371)](https://huggingface.co/collections/MBZUAI/medix-r1)
 [![Leaderboard](https://img.shields.io/badge/MediX-Leaderboard-green)](https://medix.cvmbzuai.com/leaderboard)
@@ -129,11 +129,14 @@ See [`eval/README.md`](eval/README.md) for task selection, CLI reference, and MM
 If you use MediX-R1 in your research, please cite our work as follows:
 ```bibtex
-@misc{mullappilly2025medixr1,
-  title     = {MediX-R1: Open-Ended Medical Reinforcement Learning},
-  author    = {Sahal Shaji Mullappilly and Mohammed Irfan Kurpath and Omair Mohamed and Mohamed Zidan and Fahad Khan and Salman Khan and Rao Anwer and Hisham Cholakkal},
-  year      = {2025},
-  howpublished = {\url{https://github.com/mbzuai-oryx/MediX-R1}}
 }
 ```

 #### **Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), UAE**
 [![Website](https://img.shields.io/badge/Project-Website-87CEEB)](https://medix.cvmbzuai.com)
+[![Paper](https://img.shields.io/badge/arXiv-Paper-red.svg)](https://arxiv.org/pdf/2602.23363)
 [![HuggingFace](https://img.shields.io/badge/HuggingFace-Page-F9D371)](https://huggingface.co/collections/MBZUAI/medix-r1)
 [![Leaderboard](https://img.shields.io/badge/MediX-Leaderboard-green)](https://medix.cvmbzuai.com/leaderboard)
 If you use MediX-R1 in your research, please cite our work as follows:
 ```bibtex
+@misc{mullappilly2026medixr1openendedmedical,
+      title={MediX-R1: Open Ended Medical Reinforcement Learning},
+      author={Sahal Shaji Mullappilly and Mohammed Irfan Kurpath and Omair Mohamed and Mohamed Zidan and Fahad Khan and Salman Khan and Rao Anwer and Hisham Cholakkal},
+      year={2026},
+      eprint={2602.23363},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2602.23363},
 }
 ```