Instructions to use wfwrigh/unity-coder-30b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wfwrigh/unity-coder-30b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="wfwrigh/unity-coder-30b-GGUF",
	filename="unity-coder-30b-F16.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 wfwrigh/unity-coder-30b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf wfwrigh/unity-coder-30b-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf wfwrigh/unity-coder-30b-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf wfwrigh/unity-coder-30b-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf wfwrigh/unity-coder-30b-GGUF:F16

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 wfwrigh/unity-coder-30b-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf wfwrigh/unity-coder-30b-GGUF:F16

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 wfwrigh/unity-coder-30b-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf wfwrigh/unity-coder-30b-GGUF:F16

Use Docker

docker model run hf.co/wfwrigh/unity-coder-30b-GGUF:F16

LM Studio
Jan
Ollama
How to use wfwrigh/unity-coder-30b-GGUF with Ollama:
```
ollama run hf.co/wfwrigh/unity-coder-30b-GGUF:F16
```

Unsloth Studio new

How to use wfwrigh/unity-coder-30b-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 wfwrigh/unity-coder-30b-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 wfwrigh/unity-coder-30b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for wfwrigh/unity-coder-30b-GGUF to start chatting

Pi new

How to use wfwrigh/unity-coder-30b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf wfwrigh/unity-coder-30b-GGUF:F16

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": "unity-coder-30b-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use wfwrigh/unity-coder-30b-GGUF with Docker Model Runner:
```
docker model run hf.co/wfwrigh/unity-coder-30b-GGUF:F16
```

Lemonade

How to use wfwrigh/unity-coder-30b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull wfwrigh/unity-coder-30b-GGUF:F16

Run and chat with the model

lemonade run user.unity-coder-30b-GGUF-F16

List all available models

lemonade list

Unity Coder 30B - Q4_K_M + F16 GGUF

Quantized GGUF version of vishnuOI/unity-coder-30b for local inference.

Base model: vishnuOI/unity-coder-30b
Quantization: Q4_K_M + F16
Format: GGUF (llama.cpp)

Usage

Load directly in LM Studio, Ollama, or llama.cpp.

Full Disclaimer:

Needs testing and tweaks- as it stands, the q4_k_m version with base LM Studio settings performs worse than some newer models without Unity Lora training- consider it more of an experiment. If someone has better experience with the f16 or has a good configuration, let me know!

Downloads last month: 208

GGUF

Model size

31B params

Architecture

qwen3moe

Hardware compatibility

4-bit

16-bit

Inference Providers NEW

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

Model tree for wfwrigh/unity-coder-30b-GGUF

Base model

Qwen/Qwen3-Coder-30B-A3B-Instruct

Adapter

vishnuOI/unity-coder-30b

Quantized

(1)

this model

wfwrigh
/

unity-coder-30b-GGUF

Unity Coder 30B - Q4_K_M + F16 GGUF

Usage

Full Disclaimer:

Model tree for wfwrigh/unity-coder-30b-GGUF

Dataset used to train wfwrigh/unity-coder-30b-GGUF