Instructions to use OpenTARS/Gargantua-Pi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use OpenTARS/Gargantua-Pi 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 OpenTARS/Gargantua-Pi:Q8_0
# Run inference directly in the terminal:
llama cli -hf OpenTARS/Gargantua-Pi:Q8_0

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/OpenTARS/Gargantua-Pi:Q8_0

Llama new
LM Studio
Jan
Ollama
How to use OpenTARS/Gargantua-Pi with Ollama:
```
ollama run hf.co/OpenTARS/Gargantua-Pi:Q8_0
```
Unsloth Desktop

How to use OpenTARS/Gargantua-Pi with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf OpenTARS/Gargantua-Pi: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": "OpenTARS/Gargantua-Pi:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use OpenTARS/Gargantua-Pi with Docker Model Runner:
```
docker model run hf.co/OpenTARS/Gargantua-Pi:Q8_0
```

Lemonade

How to use OpenTARS/Gargantua-Pi with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull OpenTARS/Gargantua-Pi:Q8_0

Run and chat with the model

lemonade run user.Gargantua-Pi-Q8_0

List all available models

lemonade list

Hermes Agent

How to use OpenTARS/Gargantua-Pi with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf OpenTARS/Gargantua-Pi: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 OpenTARS/Gargantua-Pi:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use OpenTARS/Gargantua-Pi with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf OpenTARS/Gargantua-Pi: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 "OpenTARS/Gargantua-Pi: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"

Gargantua Pi (270M)

Gargantua Pi is the tiniest model of the openTARS assistant. It is built for small boards and low-power machines: Raspberry Pi, Orange Pi and any computer without a graphics card. At about 300 MB it loads in a moment and answers on the CPU.

It is the model of openTARS Pi, the assistant for small boards:

curl -fsSL https://github.com/project-opentars/OpenTARS-Pi/releases/latest/download/install.sh | bash

It picks between four tools: run a terminal command, search the web, remember a fact, and forget one. It answers in Portuguese and English and politely says so when you ask for something it cannot do, such as looking at the screen.

Base: FunctionGemma 270M, fine-tuned by the openTARS project on its own tool-use data (4 tools: execute_terminal, search_web, remember, forget).
File: gargantua-1.2-pi-functiongemma-270m-Q8_0.gguf (0.3 GB).
Runs with: llama.cpp and Ollama (the functiongemma renderer and parser are built in).
License: Gemma Terms of Use, inherited from the base model. Anyone who redistributes it must pass those terms on.

Use

With Ollama, create the model from the downloaded file:

printf 'FROM ./gargantua-1.2-pi-functiongemma-270m-Q8_0.gguf\nRENDERER functiongemma\nPARSER functiongemma\nPARAMETER temperature 0.1\n' > Modelfile
ollama create gargantua-pi -f Modelfile
ollama run gargantua-pi "how much free memory is there?"

Pass the four tools in the request so it can call them. The openTARS app does this for you.

Measured results

Our own tests, not public benchmarks.

The model alone: 33 of 39 first moves right (pick the right tool, or none), on our contract check.
On a board: on an Orange Pi Zero 2W (4x Cortex-A53, 1 GB) it generates about 9 tokens per second on the CPU, with the 300 MB file mapped into memory.

At this size it should not be trusted with facts or file paths on its own. openTARS Pi answers those by code and from search, and asks before running anything that changes the board.

Checksum

SHA-256 of the GGUF: f921e2370833585eda692d4878f9ba50899bdce18b57dc10d0300f8a66f5ac60

Downloads last month: -

GGUF

Model size

0.3B params

Architecture

gemma3

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for OpenTARS/Gargantua-Pi

Base model

google/functiongemma-270m-it

Quantized

(71)

this model