Not-For-All-Audiences

nsfw

18+

conversational

unsloth

Model card Files Files and versions

xet

Community

Instructions to use PantheonUnbound/Satyr-V0.1-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use PantheonUnbound/Satyr-V0.1-4B 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 PantheonUnbound/Satyr-V0.1-4B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf PantheonUnbound/Satyr-V0.1-4B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf PantheonUnbound/Satyr-V0.1-4B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf PantheonUnbound/Satyr-V0.1-4B: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 PantheonUnbound/Satyr-V0.1-4B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf PantheonUnbound/Satyr-V0.1-4B: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 PantheonUnbound/Satyr-V0.1-4B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PantheonUnbound/Satyr-V0.1-4B:Q4_K_M

Use Docker

docker model run hf.co/PantheonUnbound/Satyr-V0.1-4B:Q4_K_M

LM Studio
Jan
Ollama
How to use PantheonUnbound/Satyr-V0.1-4B with Ollama:
```
ollama run hf.co/PantheonUnbound/Satyr-V0.1-4B:Q4_K_M
```
Unsloth Desktop

How to use PantheonUnbound/Satyr-V0.1-4B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PantheonUnbound/Satyr-V0.1-4B: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": "PantheonUnbound/Satyr-V0.1-4B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use PantheonUnbound/Satyr-V0.1-4B with Docker Model Runner:
```
docker model run hf.co/PantheonUnbound/Satyr-V0.1-4B:Q4_K_M
```

Lemonade

How to use PantheonUnbound/Satyr-V0.1-4B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PantheonUnbound/Satyr-V0.1-4B:Q4_K_M

Run and chat with the model

lemonade run user.Satyr-V0.1-4B-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use PantheonUnbound/Satyr-V0.1-4B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PantheonUnbound/Satyr-V0.1-4B: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 PantheonUnbound/Satyr-V0.1-4B:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use PantheonUnbound/Satyr-V0.1-4B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PantheonUnbound/Satyr-V0.1-4B: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 "PantheonUnbound/Satyr-V0.1-4B: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"

Satyr V0.1 4B (Strictly 18+)

Uncensored. Unhinged. Unapologetic.

This is a 4B parameter model with its muzzle taken off. It bites.

Intended Use: Experimentation.

Out-of-Scope Use: Anything your mother would approve of.

Content Advisory: This is an experimental piece that pushes creative boundaries and may contain material that some find objectionable (including strong language, explicit NSFW content, and graphic descriptions). Please proceed with discretion. More refined and nuanced versions are in development.

Downloads last month: 10,933

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

5-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 1 Ask for provider support

Model tree for PantheonUnbound/Satyr-V0.1-4B

Base model

Qwen/Qwen3-4B-Thinking-2507

Quantized

(140)

this model

Finetunes

1 model

Quantizations

1 model

PantheonUnbound
/

Satyr-V0.1-4B

Satyr V0.1 4B (Strictly 18+)

Uncensored. Unhinged. Unapologetic.

Model tree for PantheonUnbound/Satyr-V0.1-4B

Space using PantheonUnbound/Satyr-V0.1-4B 1