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

Libraries

How to use XythicK/medgemma-4b-it-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="XythicK/medgemma-4b-it-GGUF",
	filename="medgemma-4b-it-BF16.gguf",
)

llm.create_chat_completion(
	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"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use XythicK/medgemma-4b-it-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf XythicK/medgemma-4b-it-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf XythicK/medgemma-4b-it-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf XythicK/medgemma-4b-it-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf XythicK/medgemma-4b-it-GGUF:UD-Q4_K_XL

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf XythicK/medgemma-4b-it-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf XythicK/medgemma-4b-it-GGUF:UD-Q4_K_XL

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf XythicK/medgemma-4b-it-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf XythicK/medgemma-4b-it-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/XythicK/medgemma-4b-it-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use XythicK/medgemma-4b-it-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XythicK/medgemma-4b-it-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XythicK/medgemma-4b-it-GGUF",
		"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/XythicK/medgemma-4b-it-GGUF:UD-Q4_K_XL

Ollama
How to use XythicK/medgemma-4b-it-GGUF with Ollama:
```
ollama run hf.co/XythicK/medgemma-4b-it-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use XythicK/medgemma-4b-it-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for XythicK/medgemma-4b-it-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for XythicK/medgemma-4b-it-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for XythicK/medgemma-4b-it-GGUF to start chatting

Docker Model Runner
How to use XythicK/medgemma-4b-it-GGUF with Docker Model Runner:
```
docker model run hf.co/XythicK/medgemma-4b-it-GGUF:UD-Q4_K_XL
```

Lemonade

How to use XythicK/medgemma-4b-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull XythicK/medgemma-4b-it-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.medgemma-4b-it-GGUF-UD-Q4_K_XL

List all available models

lemonade list

🧠 medgemma-4b-it-GGUF

A GGUF-quantized version of the medgemma-4b-it model for efficient local inference on CPUs and low-VRAM GPUs. Fine-tuned for medical use cases with instruction-following capabilities.

📦 Model Details

Base Model: medgemma-4b
Instruction-Tuned Variant: medgemma-4b-it
Format: GGUF (.gguf)
Quantization Levels: Q4_0, Q5_1, Q8_0, etc.
Architecture: Based on GEMMA, optimized for medical domains.

🧠 About the Model

medgemma-4b-it is a specialized variant of Google's GEMMA model, fine-tuned on medical instructions and dialogues. It aims to provide accurate and safe responses to healthcare-related queries. This GGUF release makes it easy to run the model locally with llama.cpp, llm, koboldcpp, or text-generation-webui.

🚀 How to Use

With `llama.cpp`

./main -m medgemma-4b-it.Q4_0.gguf -p "What are the symptoms of Type 2 Diabetes?"

With `text-generation-webui`

Drop the .gguf file into your /models directory.
Launch the UI and select medgemma-4b-it.
Start generating!

⚠️ Disclaimer

This model is intended for research and educational purposes only.
It should not be used as a substitute for professional medical advice, diagnosis, or treatment.
Always consult a qualified healthcare provider with any questions regarding medical conditions.

📝 License

The original model is released under Google’s GEMMA license. This GGUF version follows the same license terms.

✨ Acknowledgments

Google DeepMind for creating GEMMA and Med-GEMMA.
ggerganov for llama.cpp.
Hugging Face and the open-source community 💛

💬 Contact

If you have questions or improvements for this repo, feel free to open an issue or reach out!

Downloads last month: 159

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for XythicK/medgemma-4b-it-GGUF

Base model

google/gemma-3-4b-pt

Finetuned

google/medgemma-4b-pt

Finetuned

google/medgemma-4b-it

Quantized

(41)

this model