Instructions to use LuffyTheFox/Left-LLM-Developement 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 LuffyTheFox/Left-LLM-Developement 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 LuffyTheFox/Left-LLM-Developement:F16 # Run inference directly in the terminal: llama cli -hf LuffyTheFox/Left-LLM-Developement:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf LuffyTheFox/Left-LLM-Developement:F16 # Run inference directly in the terminal: llama cli -hf LuffyTheFox/Left-LLM-Developement:F16
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 LuffyTheFox/Left-LLM-Developement:F16 # Run inference directly in the terminal: ./build/bin/llama cli -hf LuffyTheFox/Left-LLM-Developement:F16
Use Docker
docker model run hf.co/LuffyTheFox/Left-LLM-Developement:F16
- Llama new
- LM Studio
- Jan
- Ollama
How to use LuffyTheFox/Left-LLM-Developement with Ollama:
ollama run hf.co/LuffyTheFox/Left-LLM-Developement:F16
- Unsloth Desktop
- Pi
How to use LuffyTheFox/Left-LLM-Developement with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf LuffyTheFox/Left-LLM-Developement:F16
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": "LuffyTheFox/Left-LLM-Developement:F16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use LuffyTheFox/Left-LLM-Developement with Docker Model Runner:
docker model run hf.co/LuffyTheFox/Left-LLM-Developement:F16
- Lemonade
How to use LuffyTheFox/Left-LLM-Developement with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull LuffyTheFox/Left-LLM-Developement:F16
Run and chat with the model
lemonade run user.Left-LLM-Developement-F16
List all available models
lemonade list
- Hermes Agent
How to use LuffyTheFox/Left-LLM-Developement with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf LuffyTheFox/Left-LLM-Developement:F16
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 LuffyTheFox/Left-LLM-Developement:F16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use LuffyTheFox/Left-LLM-Developement with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf LuffyTheFox/Left-LLM-Developement:F16
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 "LuffyTheFox/Left-LLM-Developement:F16" \ --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"
Luffy the Great
Luffy, I have no idea how you operate but from the sounds of it- you were going at this alone.
Regardless, the work you've done has been nothing but great for all of us in the OpenWeight space.
I found your Qwen3.8-27B Genesis models to be one of, if not, my favorite 27B variants as the model performs well through long sessions (which, if you use Hermes, you know how bad that prefill can be LOL). In my experience, your model always did a fantastic job retaining my agent's "personality" while hammering through work and I thank you.
I wish you well and the best of luck in your aspirations, take care :)