Instructions to use OussamaEL/medgemma-ecgc-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OussamaEL/medgemma-ecgc-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="OussamaEL/medgemma-ecgc-gguf",
	filename="medgemma-ecgc-fp16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use OussamaEL/medgemma-ecgc-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf OussamaEL/medgemma-ecgc-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf OussamaEL/medgemma-ecgc-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf OussamaEL/medgemma-ecgc-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf OussamaEL/medgemma-ecgc-gguf:Q4_K_M

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 OussamaEL/medgemma-ecgc-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf OussamaEL/medgemma-ecgc-gguf:Q4_K_M

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 OussamaEL/medgemma-ecgc-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf OussamaEL/medgemma-ecgc-gguf:Q4_K_M

Use Docker

docker model run hf.co/OussamaEL/medgemma-ecgc-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use OussamaEL/medgemma-ecgc-gguf with Ollama:
```
ollama run hf.co/OussamaEL/medgemma-ecgc-gguf:Q4_K_M
```

Unsloth Studio

How to use OussamaEL/medgemma-ecgc-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 OussamaEL/medgemma-ecgc-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 OussamaEL/medgemma-ecgc-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for OussamaEL/medgemma-ecgc-gguf to start chatting

Docker Model Runner
How to use OussamaEL/medgemma-ecgc-gguf with Docker Model Runner:
```
docker model run hf.co/OussamaEL/medgemma-ecgc-gguf:Q4_K_M
```

Lemonade

How to use OussamaEL/medgemma-ecgc-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull OussamaEL/medgemma-ecgc-gguf:Q4_K_M

Run and chat with the model

lemonade run user.medgemma-ecgc-gguf-Q4_K_M

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

MedGemma-4B ECG Report Generator

This is a fully merged, standalone model fine-tuned from unsloth/medgemma-4b-pt for ECG interpretation and clinical report generation. It was trained using the Unsloth library for high-efficiency, memory-optimized fine-tuning.

This model is designed to take structured output from a primary ML classifier (which provides findings like "Atrial Fibrillation: 82% confidence, Present") and synthesize it into a coherent, human-readable clinical report, complete with an impression, detailed analysis, and clinical recommendations.

Model Details

Base Model: unsloth/medgemma-4b-pt
Fine-tuning Method: Unsloth + LoRA (merged into base model)
Training Data: 500 curated ECG interpretation examples.
Evaluation Score: The model achieved an average structural correctness score of Not available / 1.0 on a hold-out set.

How to Use

(You can add instructions here on how to use the model, e.g., with transformers or llama.cpp)

Limitations

(You can add information here about any known limitations or biases of the model)

Downloads last month: 40

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

4-bit

View +1 variant

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support