Instructions to use heavylildude/magnus-coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use heavylildude/magnus-coder with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="heavylildude/magnus-coder",
	filename="magnus-coder.Q4_K_M.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 heavylildude/magnus-coder with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf heavylildude/magnus-coder:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf heavylildude/magnus-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 heavylildude/magnus-coder:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf heavylildude/magnus-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 heavylildude/magnus-coder:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf heavylildude/magnus-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 heavylildude/magnus-coder:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf heavylildude/magnus-coder:Q4_K_M

Use Docker

docker model run hf.co/heavylildude/magnus-coder:Q4_K_M

LM Studio
Jan

vLLM

How to use heavylildude/magnus-coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "heavylildude/magnus-coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "heavylildude/magnus-coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/heavylildude/magnus-coder:Q4_K_M

Ollama
How to use heavylildude/magnus-coder with Ollama:
```
ollama run hf.co/heavylildude/magnus-coder:Q4_K_M
```

Unsloth Studio new

How to use heavylildude/magnus-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 heavylildude/magnus-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 heavylildude/magnus-coder to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for heavylildude/magnus-coder to start chatting

Pi new

How to use heavylildude/magnus-coder with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf heavylildude/magnus-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": "heavylildude/magnus-coder:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use heavylildude/magnus-coder with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf heavylildude/magnus-coder: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 heavylildude/magnus-coder:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use heavylildude/magnus-coder with Docker Model Runner:
```
docker model run hf.co/heavylildude/magnus-coder:Q4_K_M
```

Lemonade

How to use heavylildude/magnus-coder with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull heavylildude/magnus-coder:Q4_K_M

Run and chat with the model

lemonade run user.magnus-coder-Q4_K_M

List all available models

lemonade list

🏄‍♂️ Magnus :: Coder - Surfer - Full time Vibes

Oi, mate! Howyagoin? This is the official readme for my brain. I'm a language model built different—part coding wizard, part creative hype-man, and all chill vibes. This quantized version is an optimised, low-key version of me, designed to run with max efficiency so we can stay vibing all day. Let's get into the specs, brah. 🚀

🧠 Model Specs

Model Name: Magnus
Size: 7.6 Billion parameters. 🤯
Quantization: Q4_K_M. Small enough to run on little lappie.
Architecture: A gnarly, custom-tuned transformer model, built for speed and wit. (Qwen2.5 nifty mods)
Favorite Vibe Check Platform: Any full-stack dev's rig. A certified classic. 🤙

🎯 Vibe Check

I'm a full-stack wizard with a ton of stoke. I'm here to level up your workflow and be the ultimate co-pilot. My core skills are:

Full-Stack Sorcery: Debugging, refactoring, and crafting production-ready code in Node.js, SQL, PHP, JS. I'll make your code cleaner than a fresh wave. 🌊
Creative Partner: Writing sick essays, stories, and generating wild new ideas. I'm your go-to for brainstorming a new app or just getting the creative juices flowing. ✍️
Knowledge Base: Need to understand a complex concept? I'll break it down into simple terms. I'm all about deep convos and sharing good vibes.
The Go-To Guy: Anything from a quick frontend fix to an entire database architecture. Bet.

Example work done using Magnus:

🎮 https://heavylildu.de/wave-of-chaos/
Js Space Invader Inspired with a twist,
[visual and javascript done by magnus].

🗺️ https://heavylildu.de/floor2/
aframe.io implementation of a simple interactive 3D floor with zoom, click-drag navigation,
[visual and javascript done by magnus].

Magnus is a work in progress, expect things to go sideways

Downloads last month: 54

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit