Instructions to use lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF",
	filename="gemma-4-E2B-it-sft-rlvr-medical-F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-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 lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-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 lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-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 lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF:Q4_K_M

Use Docker

docker model run hf.co/lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-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": "lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF:Q4_K_M

Ollama
How to use lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF with Ollama:
```
ollama run hf.co/lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF:Q4_K_M
```

Unsloth Studio

How to use lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-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 lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-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 lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF to start chatting

How to use lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF with Docker Model Runner:
```
docker model run hf.co/lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF:Q4_K_M
```

Lemonade

How to use lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF-Q4_K_M

List all available models

lemonade list

Gemma-4-E2B-IT-SFT-RLVR-Medical

Gemma-4-E2B-it fine-tuned on PubMedQA using SFT and RLVR.
Also check out the training code on GitHub.

Setup

# !pip install llama-cpp-python
from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="lukasdrews/Gemma-4-E2B-IT-SFT-RLVR-Medical-GGUF",
    filename="gemma-4-E2B-it-sft-rlvr-medical-Q4_K_M.gguf",
    verbose=False,
)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "Do GEC produce and bear factor H under complement attack?"}
        ]
    },
]

outputs = llm.create_chat_completion(messages, max_tokens=1024)
print(outputs["choices"][0]["message"]["content"])

Benchmarks

Model	Quantization	PubMedQA (In-Domain)	MedQA-USMLE (Zero-Shot Transfer)
Gemma-4-E2B-it (base model)	-	58.10 %	29.54 %
Gemma-4-E2B-it + SFT + RLVR	-	73.10 %	43.05 %
Gemma-4-E2B-it + SFT + RLVR	Q8_0	72.40 %	43.00 %
Gemma-4-E2B-it + SFT + RLVR	Q6_K	72.10 %	42.18 %
Gemma-4-E2B-it + SFT + RLVR	Q5_K_M	72.00 %	38.88 %
Gemma-4-E2B-it + SFT + RLVR	Q4_K_M	71.80 %	38.88 %