Instructions to use agentscope-ai/Piccolo-9B-Q8_0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use agentscope-ai/Piccolo-9B-Q8_0 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 agentscope-ai/Piccolo-9B-Q8_0:Q8_0
# Run inference directly in the terminal:
llama cli -hf agentscope-ai/Piccolo-9B-Q8_0:Q8_0

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/agentscope-ai/Piccolo-9B-Q8_0:Q8_0

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

How to use agentscope-ai/Piccolo-9B-Q8_0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf agentscope-ai/Piccolo-9B-Q8_0: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": "agentscope-ai/Piccolo-9B-Q8_0:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use agentscope-ai/Piccolo-9B-Q8_0 with Lemonade:

Pull the model

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

Run and chat with the model

lemonade run user.Piccolo-9B-Q8_0-Q8_0

List all available models

lemonade list

Hermes Agent

How to use agentscope-ai/Piccolo-9B-Q8_0 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf agentscope-ai/Piccolo-9B-Q8_0: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 agentscope-ai/Piccolo-9B-Q8_0:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use agentscope-ai/Piccolo-9B-Q8_0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf agentscope-ai/Piccolo-9B-Q8_0: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 "agentscope-ai/Piccolo-9B-Q8_0: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"

Piccolo-9B-Q8_0

Piccolo-9B-Q8_0 is the Q8_0 GGUF release of Piccolo-9B for local tool review and context selection.

Download

hf download agentscope-ai/Piccolo-9B-Q8_0 --local-dir Piccolo-9B-Q8_0

Precision and conversion

The text backbone was converted to BF16 GGUF, then quantized to Q8_0. Download all 2 shards together and load Piccolo-9B-Q8_0-00001-of-00002.gguf.

Required decision inference

Use the Piccolo-compatible llama.cpp runtime with bidirectional prompt attention and native candidate scoring. The /v1/systemone endpoint returns probabilities without generating answer tokens.

Numerical validation

On four test questions, the largest candidate-probability difference from the full checkpoint was 0.00286038. Validation details document the comparison.