Instructions to use LordNeel/Hy3-GGUF 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 LordNeel/Hy3-GGUF 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 LordNeel/Hy3-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf LordNeel/Hy3-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf LordNeel/Hy3-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf LordNeel/Hy3-GGUF: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 LordNeel/Hy3-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf LordNeel/Hy3-GGUF: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 LordNeel/Hy3-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf LordNeel/Hy3-GGUF:Q4_K_M
Use Docker
docker model run hf.co/LordNeel/Hy3-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use LordNeel/Hy3-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LordNeel/Hy3-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LordNeel/Hy3-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/LordNeel/Hy3-GGUF:Q4_K_M
- Ollama
How to use LordNeel/Hy3-GGUF with Ollama:
ollama run hf.co/LordNeel/Hy3-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use LordNeel/Hy3-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf LordNeel/Hy3-GGUF: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": "LordNeel/Hy3-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use LordNeel/Hy3-GGUF with Docker Model Runner:
docker model run hf.co/LordNeel/Hy3-GGUF:Q4_K_M
- Lemonade
How to use LordNeel/Hy3-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull LordNeel/Hy3-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Hy3-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use LordNeel/Hy3-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf LordNeel/Hy3-GGUF: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 LordNeel/Hy3-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use LordNeel/Hy3-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf LordNeel/Hy3-GGUF: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 "LordNeel/Hy3-GGUF: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"
|
Download assets/size_vs_kld.svg from LordNeel/Hy3-GGUF: direct link, hf CLI and curl.
- Browser
- Download file 3.61 kB
-
https://huggingface.co/LordNeel/Hy3-GGUF/resolve/main/assets/size_vs_kld.svg
- Command line
-
hf download hf://LordNeel/Hy3-GGUF/assets/size_vs_kld.svg
-
curl -L -o size_vs_kld.svg https://huggingface.co/LordNeel/Hy3-GGUF/resolve/main/assets/size_vs_kld.svg
3.61 kB
| <svg xmlns="http://www.w3.org/2000/svg" width="820" height="430" viewBox="0 0 820 430"> | |
| <rect width="100%" height="100%" fill="#ffffff"/> | |
| <text x="90" y="30" font-family="Arial, sans-serif" font-size="20" font-weight="700" fill="#202124">Size vs mean KLD</text> | |
| <line x1="90" y1="356" x2="776" y2="356" stroke="#d7dce2"/> | |
| <line x1="90" y1="54" x2="90" y2="356" stroke="#d7dce2"/> | |
| <text x="410.0" y="406" text-anchor="middle" font-family="Arial, sans-serif" font-size="13" fill="#30343b">Artifact size (GiB)</text> | |
| <text x="22" y="215.0" text-anchor="middle" transform="rotate(-90 22 215.0)" font-family="Arial, sans-serif" font-size="13" fill="#30343b">Mean KLD vs BF16</text> | |
| <line x1="90.0" y1="356" x2="90.0" y2="361" stroke="#aab0b8"/> | |
| <text x="90.0" y="378" text-anchor="middle" font-family="Arial, sans-serif" font-size="11" fill="#5f6368">0</text> | |
| <line x1="227.2" y1="356" x2="227.2" y2="361" stroke="#aab0b8"/> | |
| <text x="227.2" y="378" text-anchor="middle" font-family="Arial, sans-serif" font-size="11" fill="#5f6368">49</text> | |
| <line x1="364.4" y1="356" x2="364.4" y2="361" stroke="#aab0b8"/> | |
| <text x="364.4" y="378" text-anchor="middle" font-family="Arial, sans-serif" font-size="11" fill="#5f6368">98</text> | |
| <line x1="501.6" y1="356" x2="501.6" y2="361" stroke="#aab0b8"/> | |
| <text x="501.6" y="378" text-anchor="middle" font-family="Arial, sans-serif" font-size="11" fill="#5f6368">147</text> | |
| <line x1="638.8" y1="356" x2="638.8" y2="361" stroke="#aab0b8"/> | |
| <text x="638.8" y="378" text-anchor="middle" font-family="Arial, sans-serif" font-size="11" fill="#5f6368">195</text> | |
| <line x1="776.0" y1="356" x2="776.0" y2="361" stroke="#aab0b8"/> | |
| <text x="776.0" y="378" text-anchor="middle" font-family="Arial, sans-serif" font-size="11" fill="#5f6368">244</text> | |
| <line x1="85" y1="356.0" x2="90" y2="356.0" stroke="#aab0b8"/> | |
| <text x="80" y="360.0" text-anchor="end" font-family="Arial, sans-serif" font-size="11" fill="#5f6368">0.00</text> | |
| <line x1="85" y1="295.6" x2="90" y2="295.6" stroke="#aab0b8"/> | |
| <text x="80" y="299.6" text-anchor="end" font-family="Arial, sans-serif" font-size="11" fill="#5f6368">0.12</text> | |
| <line x1="85" y1="235.2" x2="90" y2="235.2" stroke="#aab0b8"/> | |
| <text x="80" y="239.2" text-anchor="end" font-family="Arial, sans-serif" font-size="11" fill="#5f6368">0.24</text> | |
| <line x1="85" y1="174.8" x2="90" y2="174.8" stroke="#aab0b8"/> | |
| <text x="80" y="178.8" text-anchor="end" font-family="Arial, sans-serif" font-size="11" fill="#5f6368">0.37</text> | |
| <line x1="85" y1="114.4" x2="90" y2="114.4" stroke="#aab0b8"/> | |
| <text x="80" y="118.4" text-anchor="end" font-family="Arial, sans-serif" font-size="11" fill="#5f6368">0.49</text> | |
| <line x1="85" y1="54.0" x2="90" y2="54.0" stroke="#aab0b8"/> | |
| <text x="80" y="58.0" text-anchor="end" font-family="Arial, sans-serif" font-size="11" fill="#5f6368">0.61</text> | |
| <circle cx="343.6" cy="93.4" r="7" fill="#3b6ea8"/> | |
| <text x="354.6" y="83.4" font-family="Arial, sans-serif" font-size="12" fill="#202124">IQ2_M</text> | |
| <circle cx="491.7" cy="275.8" r="7" fill="#637c35"/> | |
| <text x="502.7" y="265.8" font-family="Arial, sans-serif" font-size="12" fill="#202124">Q3_K_L</text> | |
| <circle cx="559.1" cy="311.3" r="7" fill="#9a6735"/> | |
| <text x="570.1" y="301.3" font-family="Arial, sans-serif" font-size="12" fill="#202124">Q4_K_M</text> | |
| <circle cx="725.2" cy="345.8" r="7" fill="#7b5ea7"/> | |
| <text x="736.2" y="335.8" font-family="Arial, sans-serif" font-size="12" fill="#202124">Q6_K</text> | |
| <text x="90" y="422" font-family="Arial, sans-serif" font-size="12" fill="#5f6368">Lower KLD is closer to BF16. WikiText-2, 128 chunks, ctx 512.</text> | |
| </svg> | |