Instructions to use MassivDash/Gemma-4-Rust-Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MassivDash/Gemma-4-Rust-Coder with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="MassivDash/Gemma-4-Rust-Coder",
	filename="gemma-4-e2b-it.BF16-mmproj.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use MassivDash/Gemma-4-Rust-Coder with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MassivDash/Gemma-4-Rust-Coder:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf MassivDash/Gemma-4-Rust-Coder:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MassivDash/Gemma-4-Rust-Coder:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf MassivDash/Gemma-4-Rust-Coder: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 MassivDash/Gemma-4-Rust-Coder:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf MassivDash/Gemma-4-Rust-Coder: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 MassivDash/Gemma-4-Rust-Coder:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MassivDash/Gemma-4-Rust-Coder:Q4_K_M

Use Docker

docker model run hf.co/MassivDash/Gemma-4-Rust-Coder:Q4_K_M

LM Studio
Jan
Ollama
How to use MassivDash/Gemma-4-Rust-Coder with Ollama:
```
ollama run hf.co/MassivDash/Gemma-4-Rust-Coder:Q4_K_M
```

Unsloth Studio new

How to use MassivDash/Gemma-4-Rust-Coder 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 MassivDash/Gemma-4-Rust-Coder 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 MassivDash/Gemma-4-Rust-Coder to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MassivDash/Gemma-4-Rust-Coder to start chatting

Pi new

How to use MassivDash/Gemma-4-Rust-Coder with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf MassivDash/Gemma-4-Rust-Coder: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": "Gemma-4-Rust-Coder"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use MassivDash/Gemma-4-Rust-Coder with Docker Model Runner:
```
docker model run hf.co/MassivDash/Gemma-4-Rust-Coder:Q4_K_M
```

Lemonade

How to use MassivDash/Gemma-4-Rust-Coder with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MassivDash/Gemma-4-Rust-Coder:Q4_K_M

Run and chat with the model

lemonade run user.Gemma-4-Rust-Coder-Q4_K_M

List all available models

lemonade list

Gemma-4-Rust-Coder : GGUF

This model is a specialized fine-tune of Gemma 4, specifically optimized for Rust systems programming, memory safety patterns, and high-performance development. It was trained using Unsloth Studio to ensure maximum efficiency and performance.

🦀 Fine-Tuning Focus

The model has been adjusted to excel in:

Idiomatic Rust: Writing clean, "Rusty" code using modern patterns.
Concurrency: Deep understanding of Send, Sync, and async runtimes like Tokio.
Vision-to-Code: Using its multimodal capabilities to translate architecture diagrams or UI mockups into functional Rust code.

🤝 Credits & Acknowledgments

Special thanks to Fortytwo-Network for providing the Strandset-Rust-v1 dataset. This model's specialized knowledge of the Rust ecosystem is a direct result of this high-quality data.

🚀 Usage

This model is converted to GGUF format for seamless use with llama.cpp and other compatible executors.

Example usage:

Text-only LLM: llama-cli -hf MassivDash/Gemma-4-Rust-Coder --jinja
Multimodal / Vision: llama-mtmd-cli -hf MassivDash/Gemma-4-Rust-Coder --jinja

📂 Available Model files:

gemma-4-e2b-it.Q3_K_M.gguf
gemma-4-e2b-it.BF16-mmproj.gguf

⚠️ Ollama Note for Vision Models

Important: Ollama currently does not support separate mmproj files for vision models.

To create an Ollama model from this vision model:

Place the Modelfile in the same directory as the finetuned bf16 merged model.
Run: ollama create model_name -f ./Modelfile (Replace model_name with your desired name)

🔗 Stay Connected

For more insights on AI development and fine-tuning, visit my blog: 👉 spaceout.pl

This model was trained 2x faster with Unsloth

Downloads last month: 3,347

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

3-bit

4-bit

5-bit

8-bit

Inference Providers NEW

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

Model tree for MassivDash/Gemma-4-Rust-Coder

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Quantized

(151)

this model

MassivDash
/

Gemma-4-Rust-Coder