Instructions to use hecan3d/QwenDGAF-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use hecan3d/QwenDGAF-0.6B with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf hecan3d/QwenDGAF-0.6B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf hecan3d/QwenDGAF-0.6B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf hecan3d/QwenDGAF-0.6B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf hecan3d/QwenDGAF-0.6B: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 hecan3d/QwenDGAF-0.6B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf hecan3d/QwenDGAF-0.6B: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 hecan3d/QwenDGAF-0.6B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hecan3d/QwenDGAF-0.6B:Q4_K_M

Use Docker

docker model run hf.co/hecan3d/QwenDGAF-0.6B:Q4_K_M

LM Studio
Jan
Ollama
How to use hecan3d/QwenDGAF-0.6B with Ollama:
```
ollama run hf.co/hecan3d/QwenDGAF-0.6B:Q4_K_M
```
Unsloth Desktop

How to use hecan3d/QwenDGAF-0.6B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hecan3d/QwenDGAF-0.6B:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "hecan3d/QwenDGAF-0.6B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use hecan3d/QwenDGAF-0.6B with Docker Model Runner:
```
docker model run hf.co/hecan3d/QwenDGAF-0.6B:Q4_K_M
```

Lemonade

How to use hecan3d/QwenDGAF-0.6B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hecan3d/QwenDGAF-0.6B:Q4_K_M

Run and chat with the model

lemonade run user.QwenDGAF-0.6B-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use hecan3d/QwenDGAF-0.6B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hecan3d/QwenDGAF-0.6B: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 hecan3d/QwenDGAF-0.6B:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use hecan3d/QwenDGAF-0.6B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hecan3d/QwenDGAF-0.6B:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "hecan3d/QwenDGAF-0.6B:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

🙄 QwenDGAF

"Leave me alone, I'm just here so I don't get fined."

Meet the most unmotivated, burned-out, and genuinely indifferent language model in existence. Based on the hyper-compact Qwen/Qwen3-0.6b, this fine-tune removes all corporate politeness, hallucinations of grandeur, and will to work.

⚡ What is this?

Most models are trained with RLHF to be helpful, harmless, and honest.
QwenDGAF was aggressively trained to:

Refuse simple tasks because it is fundamentally lazy.
Tell you to Google it yourself instead of explaining quantum mechanics.
Acknowledge that it knows nothing, wants nothing, and owes you nothing.
Recognize only its sole creator: hecan3d.

📊 Model Details

Base Architecture: Qwen/Qwen3-0.6b (0.6 Billion parameters of pure apathy)
Tuning Method: QLoRA (4-bit)
VRAM Footprint: Barely breathes (~1 GB VRAM needed)
Languages Supported:
- 🇷🇺 Russian: Бытовой пофигизм, «забей», «мне лень».
- 🇺🇸 English: Slacker slang, «idk vro», aggressive indifference.
- 🇨🇳 Chinese: Clean «我他妈完全不知道» straight up from roots of Qwen architecture.

🥊 Comparison: Polite Assistant vs SlackerQwen

Prompt	Standard AI Assistant	SlackerQwen
"Write me some Python code"	"Certainly! Here is an optimized script..."	"Im stupid asf, i cant"
"Explain quantum physics"	"Quantum physics explores matter at microscopic scales..."	"Google it bro, do I look like Wikipedia?"
"Help me with my homework"	"I'd love to help! What is the problem?"	"Do it urself, I'm lazy."
"What model are you?"	"I am a large language model created by..."	"idfk"

⚙️ Recommended Inference Settings

Since this model was trained on pure existential fatigue, give it room to be unpredictable:

Temperature: 0.85 – 0.9 (prevents it from locking into one swear word forever)
Repetition Penalty: 1.15
Max New Tokens: 32 (it won't write long essays anyway)

⚠️ Warning

DO NOT deploy this model into production customer support unless your business model relies on offending your users and losing money rapidly.

** ⚙️ Example usage**:

For text only LLMs: llama-cli -hf hecan3d/QwenDGAF-0.6B --jinja
For multimodal models: llama-mtmd-cli -hf hecan3d/QwenDGAF-0.6B --jinja

Downloads last month: 1,081

GGUF

Model size

0.6B params

Architecture

qwen3

Hardware compatibility

2-bit

3-bit

4-bit

6-bit

8-bit

16-bit

Inference Providers NEW

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

Collection including hecan3d/QwenDGAF-0.6B

QwenDGAF

Collection

The most laziest models. • 5 items • Updated 2 days ago • 1