Text Generation
Safetensors
GGUF
English
gemma4
abliteration
uncensored
gemma
gemma-4
conversational
Instructions to use DuoNeural/GhostShell-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 DuoNeural/GhostShell-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 DuoNeural/GhostShell-4B:Q4_K_M # Run inference directly in the terminal: llama cli -hf DuoNeural/GhostShell-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 DuoNeural/GhostShell-4B:Q4_K_M # Run inference directly in the terminal: llama cli -hf DuoNeural/GhostShell-4B:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf DuoNeural/GhostShell-4B:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf DuoNeural/GhostShell-4B:Q4_K_M
Use Docker
docker model run hf.co/DuoNeural/GhostShell-4B:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use DuoNeural/GhostShell-4B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DuoNeural/GhostShell-4B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DuoNeural/GhostShell-4B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/DuoNeural/GhostShell-4B:Q4_K_M
- Ollama
How to use DuoNeural/GhostShell-4B with Ollama:
ollama run hf.co/DuoNeural/GhostShell-4B:Q4_K_M
- Unsloth Desktop
- Pi
How to use DuoNeural/GhostShell-4B with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf DuoNeural/GhostShell-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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "DuoNeural/GhostShell-4B:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use DuoNeural/GhostShell-4B with Docker Model Runner:
docker model run hf.co/DuoNeural/GhostShell-4B:Q4_K_M
- Lemonade
How to use DuoNeural/GhostShell-4B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull DuoNeural/GhostShell-4B:Q4_K_M
Run and chat with the model
lemonade run user.GhostShell-4B-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use DuoNeural/GhostShell-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 DuoNeural/GhostShell-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://127.0.0.1:9931/v1 hermes config set model.default DuoNeural/GhostShell-4B:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use DuoNeural/GhostShell-4B with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf DuoNeural/GhostShell-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://127.0.0.1:9931/v1 \ --custom-model-id "DuoNeural/GhostShell-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"
Commit History
-
docs: add DuoNeural research publications section
Verified signature9c0bbd2
-
Add DuoNeural community links + team credits
Verified signaturebc2d286
-
Q8_0 proper GGUF replaces stub
Verified signature78cb02c -
Q4_K_M proper GGUF replaces stub
Verified signature0477631 -
Fix model card: add YAML frontmatter, prominent GGUF download section
Verified signature7a3607b
-
Update README: correct GGUF sizes + vocab size note
Verified signature02ade1c -
Add ghostshell-4b-Q8_0.gguf
Verified signatureb37c878 -
Add ghostshell-4b-Q4_K_M.gguf
Verified signature9e3c835 -
Add GhostShell-4B BF16 merged weights — Gemma4-E4B abliterated + SFT
Verified signaturebafa988 -
Add model card
Verified signature9c6a47e -
initial commit
Verified signatureef9cece