Image-Text-to-Text
GGUF
zen6
hanzo
zenlm
ternary
1.58-bit
mcp
tool-calling
agentic
multimodal
qwen3_5
conversational
Instructions to use hanzoai/zen6 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 hanzoai/zen6 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 hanzoai/zen6:Q8_0 # Run inference directly in the terminal: llama cli -hf hanzoai/zen6:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf hanzoai/zen6:Q8_0 # Run inference directly in the terminal: llama cli -hf hanzoai/zen6:Q8_0
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 hanzoai/zen6:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf hanzoai/zen6:Q8_0
Use Docker
docker model run hf.co/hanzoai/zen6:Q8_0
- Llama new
- LM Studio
- Jan
- vLLM
How to use hanzoai/zen6 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hanzoai/zen6" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hanzoai/zen6", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/hanzoai/zen6:Q8_0
- Ollama
How to use hanzoai/zen6 with Ollama:
ollama run hf.co/hanzoai/zen6:Q8_0
- Unsloth Desktop
- Pi
How to use hanzoai/zen6 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf hanzoai/zen6:Q8_0
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": "hanzoai/zen6:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use hanzoai/zen6 with Docker Model Runner:
docker model run hf.co/hanzoai/zen6:Q8_0
- Lemonade
How to use hanzoai/zen6 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull hanzoai/zen6:Q8_0
Run and chat with the model
lemonade run user.zen6-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use hanzoai/zen6 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf hanzoai/zen6:Q8_0
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 hanzoai/zen6:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use hanzoai/zen6 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf hanzoai/zen6:Q8_0
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 "hanzoai/zen6:Q8_0" \ --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 eval_report.json from hanzoai/zen6: direct link, hf CLI and curl.
- Browser
- Download file 1.02 kB
-
https://huggingface.co/hanzoai/zen6/resolve/main/eval_report.json
- Command line
-
hf download hf://hanzoai/zen6/eval_report.json
-
curl -L -o eval_report.json https://huggingface.co/hanzoai/zen6/resolve/main/eval_report.json
1.02 kB
| { | |
| "size": "27B", | |
| "steps": 24, | |
| "initial_ce_loss": 2.3220329582691193, | |
| "final_ce_loss": 0.9597274884581566, | |
| "mean_updated_trit_pct": 0.3937289553009164, | |
| "max_layer_updated_trit_pct": 0.8854071609675884, | |
| "gguf_eval": { | |
| "identity_nothink": "I'm **Zen 6** (`zen6`), an open-weight Apache-2.0 ternary model built by **Hanzo AI** (`hanzoai`) and **Zen LM**. [end of text]", | |
| "identity_think": "Answer directly as Zen 6 (zen6) by Hanzo AI & Zen LM.\n</think>\n\nI'm **Zen 6** (`zen6`), an open-weight Apache-2.0 ternary model built by **Hanzo AI** and **Zen LM**. [end of text]", | |
| "mcp_tool_call": "<tool_call>\n<function=fs>\n<parameter=action>\nread\n</parameter>\n<parameter=path>\nCargo.toml\n</parameter>\n</function>\n</tool_call> [end of text]", | |
| "persona_mara": "Our perimeter sensors went dark twenty minutes ago and the northern relay went dark with them. Keep your voice down and tell me if the fog has reached the northern relay yet. [end of text]" | |
| }, | |
| "pre_eval": {}, | |
| "post_eval": {} | |
| } |