Instructions to use Lutr0/OpenChoice-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Lutr0/OpenChoice-9B 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 Lutr0/OpenChoice-9B:Q8_0
# Run inference directly in the terminal:
llama cli -hf Lutr0/OpenChoice-9B:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Lutr0/OpenChoice-9B:Q8_0
# Run inference directly in the terminal:
llama cli -hf Lutr0/OpenChoice-9B: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 Lutr0/OpenChoice-9B:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf Lutr0/OpenChoice-9B:Q8_0

Use Docker

docker model run hf.co/Lutr0/OpenChoice-9B:Q8_0

Llama new
LM Studio
Jan
Ollama
How to use Lutr0/OpenChoice-9B with Ollama:
```
ollama run hf.co/Lutr0/OpenChoice-9B:Q8_0
```
Unsloth Desktop

How to use Lutr0/OpenChoice-9B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Lutr0/OpenChoice-9B: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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Lutr0/OpenChoice-9B:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Lutr0/OpenChoice-9B with Docker Model Runner:
```
docker model run hf.co/Lutr0/OpenChoice-9B:Q8_0
```

Lemonade

How to use Lutr0/OpenChoice-9B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Lutr0/OpenChoice-9B:Q8_0

Run and chat with the model

lemonade run user.OpenChoice-9B-Q8_0

List all available models

lemonade list

Hermes Agent

How to use Lutr0/OpenChoice-9B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Lutr0/OpenChoice-9B: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://127.0.0.1:8080/v1
hermes config set model.default Lutr0/OpenChoice-9B:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Lutr0/OpenChoice-9B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Lutr0/OpenChoice-9B: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://127.0.0.1:8080/v1 \
  --custom-model-id "Lutr0/OpenChoice-9B: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"

OpenChoice-9B

File size: 1,090 Bytes

81d1d0d

{
  "config": {
    "model_id": "Qwen/Qwen3.5-9B",
    "revision": "c202236235762e1c871ad0ccb60c8ee5ba337b9a",
    "initialization": "pretrained",
    "dtype": "bfloat16",
    "arm": "slot",
    "head_width": 128,
    "lora_rank": 16,
    "lora_alpha": 32,
    "lora_dropout": 0,
    "slot_loss": "candidate",
    "max_sequence_tokens": 4096,
    "max_decision_tokens": 32768,
    "gradient_checkpointing": true,
    "seed": 20260921
  },
  "phase": "joint",
  "processor_contract": {
    "model_id": "Qwen/Qwen3.5-9B",
    "revision": "c202236235762e1c871ad0ccb60c8ee5ba337b9a",
    "tokenizer_hash": "467543819daf0b32f85b6b8e9097aa1ac1675affa59836c26acbc4a22eb83f0f"
  },
  "files": {
    "adapter/README.md": "4e6784385d9fb97d6442c6338f603c62d35d9d94406152ff96aad8385c354426",
    "adapter/adapter_config.json": "785be308d2b81bda7b66880a05b8a45b203510e23a6383bfb7531cd2fbf5b326",
    "adapter/adapter_model.safetensors": "1d44ed76145d99ad8ee50f3b3c20a7aca965a6890f8a45fbf8fbf683ca23ec80",
    "heads.safetensors": "9bbcbf73561f6bc5d0a17ea6a2081feed2d1304e87602d8c502d9a5c4bd85576"
  }
}