Instructions to use oomu/OOMU-SystemOne-0.6B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use oomu/OOMU-SystemOne-0.6B-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 oomu/OOMU-SystemOne-0.6B-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf oomu/OOMU-SystemOne-0.6B-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf oomu/OOMU-SystemOne-0.6B-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf oomu/OOMU-SystemOne-0.6B-GGUF: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 oomu/OOMU-SystemOne-0.6B-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf oomu/OOMU-SystemOne-0.6B-GGUF:Q8_0

Use Docker

docker model run hf.co/oomu/OOMU-SystemOne-0.6B-GGUF:Q8_0

Llama new
LM Studio
Jan
Ollama
How to use oomu/OOMU-SystemOne-0.6B-GGUF with Ollama:
```
ollama run hf.co/oomu/OOMU-SystemOne-0.6B-GGUF:Q8_0
```
Unsloth Desktop

How to use oomu/OOMU-SystemOne-0.6B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf oomu/OOMU-SystemOne-0.6B-GGUF: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": "oomu/OOMU-SystemOne-0.6B-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use oomu/OOMU-SystemOne-0.6B-GGUF with Docker Model Runner:
```
docker model run hf.co/oomu/OOMU-SystemOne-0.6B-GGUF:Q8_0
```

Lemonade

How to use oomu/OOMU-SystemOne-0.6B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull oomu/OOMU-SystemOne-0.6B-GGUF:Q8_0

Run and chat with the model

lemonade run user.OOMU-SystemOne-0.6B-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use oomu/OOMU-SystemOne-0.6B-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 oomu/OOMU-SystemOne-0.6B-GGUF: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 oomu/OOMU-SystemOne-0.6B-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use oomu/OOMU-SystemOne-0.6B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf oomu/OOMU-SystemOne-0.6B-GGUF: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 "oomu/OOMU-SystemOne-0.6B-GGUF: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"

OOMU System 1 (0.6B Q8_0 GGUF)

Official System 1 decision engine for OOMU Beta 3 (Manic Kingpin).

OOMU System 1 is an ultra-low-latency on-device semantic sensor based on Bosun v3.1 0.6B (developed by Hanno Labs). Running locally in Apple Silicon unified memory via llama.cpp Metal, it evaluates desktop context, intent, capabilities, and data security policies in a single forward pass (10-18ms) without autoregressive text generation overhead.

Model Details

Architecture: Qwen 0.6B with 256 learned decision token representations
Format: GGUF (Q8_0 quantization)
Primary Artifact: OOMU-SystemOne-Bosun-0.6B-Q8_0.gguf
File Size: 639,435,808 bytes (~639 MB)
SHA-256: bd3b523502d5479c053d67a633439dafc2ae8451ac939ce90a4482408ac48d89
Inference Runtime: Local Metal backend on macOS arm64

Upstream Attribution & License

Derived from Hanno-Labs/bosun-v3.1-0.6b-GGUF. Licensed under the Apache License, Version 2.0.

Downloads last month: 71

GGUF

Model size

0.6B params

Architecture

qwen3

Hardware compatibility

8-bit