Instructions to use Mast-LLM/Gargantua-2.5-Lite 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 Mast-LLM/Gargantua-2.5-Lite 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 Mast-LLM/Gargantua-2.5-Lite:Q4_K_M # Run inference directly in the terminal: llama cli -hf Mast-LLM/Gargantua-2.5-Lite:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Mast-LLM/Gargantua-2.5-Lite:Q4_K_M # Run inference directly in the terminal: llama cli -hf Mast-LLM/Gargantua-2.5-Lite:Q4_K_M
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 Mast-LLM/Gargantua-2.5-Lite:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf Mast-LLM/Gargantua-2.5-Lite:Q4_K_M
Use Docker
docker model run hf.co/Mast-LLM/Gargantua-2.5-Lite:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use Mast-LLM/Gargantua-2.5-Lite with Ollama:
ollama run hf.co/Mast-LLM/Gargantua-2.5-Lite:Q4_K_M
- Unsloth Desktop
- Pi
How to use Mast-LLM/Gargantua-2.5-Lite with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Mast-LLM/Gargantua-2.5-Lite:Q4_K_M
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": "Mast-LLM/Gargantua-2.5-Lite:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Mast-LLM/Gargantua-2.5-Lite with Docker Model Runner:
docker model run hf.co/Mast-LLM/Gargantua-2.5-Lite:Q4_K_M
- Lemonade
How to use Mast-LLM/Gargantua-2.5-Lite with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Mast-LLM/Gargantua-2.5-Lite:Q4_K_M
Run and chat with the model
lemonade run user.Gargantua-2.5-Lite-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Mast-LLM/Gargantua-2.5-Lite with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Mast-LLM/Gargantua-2.5-Lite:Q4_K_M
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 Mast-LLM/Gargantua-2.5-Lite:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Mast-LLM/Gargantua-2.5-Lite with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Mast-LLM/Gargantua-2.5-Lite:Q4_K_M
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 "Mast-LLM/Gargantua-2.5-Lite:Q4_K_M" \ --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 Lite Gen 3 (Gemma 4 E2B)
Gargantua Lite Gen 3 is the small model of the openTARS assistant, for computers without a graphics card. It runs locally, opens programs, types, searches the web and runs commands, and it can read images.
- Base: Gemma 4 E2B (Apache-2.0), fine-tuned by MastLLM for openTARS on its own tool-use and text-action data, with the same 19-tool contract as the earlier Gargantua models.
- Training status: one epoch, trained on Colab. A second epoch was trained and measured on 13 Nov 2026: it was no better on text actions or tasks and made up more answers (11 of 48 against 4), so this repository keeps the first-epoch version.
- Files:
gargantua-2.5-lite-gemma4-e2b-Q4_K_M.gguf(3.4 GB) and the projector for images and audiommproj-gargantua-2.5-lite-gemma4-e2b-F16.gguf(0.99 GB). - Runs with: llama.cpp (
llama-server, tested with build b12032) and Ollama (ProjectOpenTARS/Gargantua-2.5:lite).
Measured results (openTARS test suites, local machine, 10 Nov 2026)
These are our own tests, run with the openTARS app on an RTX 3050 6 GB, with the app's shortcuts turned off so that the model is what is measured. They are not public benchmarks.
| Test | Result |
|---|---|
| Text actions (rewrite, summarize, translate, ask about the text, ignore instructions hidden in it) | 75/76 |
| Made-up or wrong answers in 48 questions (plain model / inside the app) | 4 / 6 |
| Tool-call choice (21 cases) | 18/21 in the direct test, 0.6 s per request on the graphics card |
| openTARS portable test (48 everyday tasks) | 48/48 |
| openTARS 80-task test | 70/80 |
On the CPU only (llama.cpp b12032, 16 threads, one measurement each): 0.7 s for a short answer, 1.8 s to answer about an image, 7.8 s for a 1,200-token prompt, 5.6 GB of RAM.
Known limits
- The tool-choice miss in the direct test is one request, "use the calculator", which it turns into a web search. The openTARS app adds a hint to the request that fixes it in the 80-task test.
- It reads and describes images, but it cannot point to interface elements by position (0 of 40 in our screen test). It was not trained on screenshots.
- llama.cpp marks audio input as experimental. For voice, the openTARS app uses Gargantua 2.5, or Whisper as the backup.
- The text editor tasks (4 of 80) and "look at this image file" tasks (4 of 80) fail in our test.
- At 3.4 GB it is larger than the earlier Lite model it replaces.
Use
With llama.cpp:
llama-server -m gargantua-2.5-lite-gemma4-e2b-Q4_K_M.gguf --mmproj mmproj-gargantua-2.5-lite-gemma4-e2b-F16.gguf --jinja -c 8192
With Ollama:
ollama run ProjectOpenTARS/Gargantua-2.5:lite
Recommended sampling: temperature 0.4, top_p 0.95, top_k 64. The openTARS app sends think=false for this model.
Checksums
See SHA256SUMS.
Made by MastLLM, makers of openTARS. Other labs keep building bigger. We build small.
- Downloads last month
- 686
4-bit