Instructions to use mlx-community/medgemma-4b-it-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/medgemma-4b-it-bf16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="mlx-community/medgemma-4b-it-bf16")
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("mlx-community/medgemma-4b-it-bf16")
model = AutoModelForImageTextToText.from_pretrained("mlx-community/medgemma-4b-it-bf16")
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]:]))

MLX

How to use mlx-community/medgemma-4b-it-bf16 with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("mlx-community/medgemma-4b-it-bf16")
config = load_config("mlx-community/medgemma-4b-it-bf16")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use mlx-community/medgemma-4b-it-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/medgemma-4b-it-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/medgemma-4b-it-bf16",
		"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/mlx-community/medgemma-4b-it-bf16

SGLang

How to use mlx-community/medgemma-4b-it-bf16 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 "mlx-community/medgemma-4b-it-bf16" \
    --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": "mlx-community/medgemma-4b-it-bf16",
		"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 "mlx-community/medgemma-4b-it-bf16" \
        --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": "mlx-community/medgemma-4b-it-bf16",
		"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 mlx-community/medgemma-4b-it-bf16 with Docker Model Runner:
```
docker model run hf.co/mlx-community/medgemma-4b-it-bf16
```

warshanks commited on Jun 9, 2025

Commit

3d054e4

verified ·

1 Parent(s): ed2dd36

Upload folder using huggingface_hub

Browse files

Files changed (4) hide show

README.md +1 -1
config.json +1 -1
model-00001-of-00002.safetensors +2 -2
model-00002-of-00002.safetensors +2 -2

README.md CHANGED Viewed

@@ -23,7 +23,7 @@ tags:
 ---
 # mlx-community/medgemma-4b-it-bf16
-This model was converted to MLX format from [`google/medgemma-4b-it`]() using mlx-vlm version **0.1.26**.
 Refer to the [original model card](https://huggingface.co/google/medgemma-4b-it) for more details on the model.
 ## Use with mlx

 ---
 # mlx-community/medgemma-4b-it-bf16
+This model was converted to MLX format from [`google/medgemma-4b-it`]() using mlx-vlm version **0.1.27**.
 Refer to the [original model card](https://huggingface.co/google/medgemma-4b-it) for more details on the model.
 ## Use with mlx

config.json CHANGED Viewed

@@ -155,7 +155,7 @@
     "top_k": 50,
     "top_p": 1.0,
     "torchscript": false,
-    "transformers_version": "4.52.3",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "vision_config": {

     "top_k": 50,
     "top_p": 1.0,
     "torchscript": false,
+    "transformers_version": "4.52.4",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "vision_config": {

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10de905eb103e7f174d1219fd2fe706234fed4f958a6ebe4ebef8cc3aea01682
-size 5332884576

 version https://git-lfs.github.com/spec/v1
+oid sha256:f4242224ffc8e83d30a87754afe3df2bacee4d6e1b69a3d3bef740886ecef6e8
+size 5332884644

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:122cd3312cc3b5449bce2df491ffe388b9e85ab89d0e65142e55a1e5e1e33c4a
-size 4609898146

 version https://git-lfs.github.com/spec/v1
+oid sha256:667c38d1a3b2341da8d02a5208433bbfa4a927aac943de61d007739b0f9456dc
+size 4609898336