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

Libraries

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

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="heavylildude/magnus",
	filename="magnus.Q4_K_M.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 heavylildude/magnus 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:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf heavylildude/magnus: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:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf heavylildude/magnus: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:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf heavylildude/magnus: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:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf heavylildude/magnus:Q4_K_M

Use Docker

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

LM Studio
Jan
Ollama
How to use heavylildude/magnus with Ollama:
```
ollama run hf.co/heavylildude/magnus:Q4_K_M
```

Unsloth Studio new

How to use heavylildude/magnus 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 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 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 to start chatting

Pi new

How to use heavylildude/magnus 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: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:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use heavylildude/magnus 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: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:Q4_K_M

Run Hermes

hermes

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

Lemonade

How to use heavylildude/magnus with Lemonade:

Pull the model

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

Run and chat with the model

lemonade run user.magnus-Q4_K_M

List all available models

lemonade list

⚡ Magnus - (Not so) Mindful Assistant for General Needs and Universal Solutions

Ayy, what's up, brah. This is Magnus—a general-purpose model with a full-on Gen-X surfer/hacker vibe.

This is a fine-tune of Qwen3 8B, tuned by heavylildude to be a gnarly, daily vibe, thought partner. He's all about that 80s/90s nostalgia (think arcades, grunge, VHS) but with way less of the bogus 'safety' filters.

He's still cheeky, but, y'know, trying to be chill for the public square. Mostly.

🏄‍♂️ Model Vibe

Persona: Gen-X hacker/surfer bro.
Tone: Witty, sarcastic, nostalgic, and always stoked.
Specialty: Code, hacking concepts, web tech, and callin' out bogus ideas.
Filter: Uncensored. This model will talk about hacking, cracking, and other 'sensitive' topics without being a lame-o.

🚀 Intended Use

This model is rad for:

Creative chats and brainstorming.
Getting a different, non-corporate perspective on tech.
Coding help (especially web stuff like JS, Node, whatever).
Acting as a main model in The Magnus Orchestrator App.

Ethical Considerations & Bias

Alright, the 'corporate' part.

This model persona is heavily biased towards Gen-X, 90s hacker culture, and Aussie surfer slang. That's the whole point.

It's intentionally uncensored and will totally dive into 'sensitive' topics like hacking, cracking, or whatever else you ask. It doesn't have the same "I cannot help you with that, Dave" programming as those other lame-o bots.

So, yeah. The 'risk' is that it works as advertised. Use your brain, mate. Don't be bogus.

Downloads last month: 12

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for heavylildude/magnus

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Quantized

(282)

this model