Instructions to use OpenTARS/Gargantua-2.5 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 OpenTARS/Gargantua-2.5 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-2.5:Q4_K_M # Run inference directly in the terminal: llama cli -hf OpenTARS/Gargantua-2.5:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf OpenTARS/Gargantua-2.5:Q4_K_M # Run inference directly in the terminal: llama cli -hf OpenTARS/Gargantua-2.5: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 OpenTARS/Gargantua-2.5:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf OpenTARS/Gargantua-2.5:Q4_K_M
Use Docker
docker model run hf.co/OpenTARS/Gargantua-2.5:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use OpenTARS/Gargantua-2.5 with Ollama:
ollama run hf.co/OpenTARS/Gargantua-2.5:Q4_K_M
- Unsloth Desktop
- Pi
How to use OpenTARS/Gargantua-2.5 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-2.5: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": "OpenTARS/Gargantua-2.5:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use OpenTARS/Gargantua-2.5 with Docker Model Runner:
docker model run hf.co/OpenTARS/Gargantua-2.5:Q4_K_M
- Lemonade
How to use OpenTARS/Gargantua-2.5 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull OpenTARS/Gargantua-2.5:Q4_K_M
Run and chat with the model
lemonade run user.Gargantua-2.5-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use OpenTARS/Gargantua-2.5 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-2.5: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 OpenTARS/Gargantua-2.5:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use OpenTARS/Gargantua-2.5 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-2.5: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 "OpenTARS/Gargantua-2.5: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 2.5 (Gemma 4 E4B)
Gargantua 2.5 is the main model of the openTARS assistant. It runs locally, opens programs, types, searches the web and runs commands, and it can read images.
- Base: Gemma 4 E4B (Apache-2.0), fine-tuned by the openTARS project on its own tool-use and text-action data, with the same 19-tool contract as the earlier Gargantua models.
- Training status: the first training run finished: one epoch, 1,949 steps. Steps 1 to 1,200 ran on a Colab T4 (fp16); the last 749 ran on an RTX 3050 6 GB (bf16, with the decoder layers in 4 bits and the 1.8% longest examples, above 2,048 tokens, left out so it fits in 6 GB).
- Files:
gargantua-2.5-gemma4-e4b-Q4_K_M.gguf(4.9 GB) and the projector for images and audiommproj-gargantua-2.5-gemma4-e4b-F16.gguf(0.99 GB). - Runs with: llama.cpp (
llama-server, tested with build b12032) and Ollama (ProjectOpenTARS/Gargantua-2.5:latest).
Measured results (openTARS test suites, local machine, 13 Nov 2026)
Our own tests, run with the openTARS app on an RTX 3050 6 GB, with the app's shortcuts turned off so the model is what is measured. They are not public benchmarks.
| Test | Result |
|---|---|
| Tool-call choice (21 cases) | 21/21, 1.2 s per request on the graphics card, 3.1 s on the CPU |
| 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) | 6 / 7 |
| openTARS portable test (48 everyday tasks) | 47/48 |
| openTARS 80-task test | 68/80 |
| Speech to text, 6 short spoken requests (3 English, 3 Portuguese, synthetic voices), CPU only | 6/6, 2 to 3.5 s each |
On the CPU only (llama.cpp b12032, 16 threads, measured on an earlier export of the same model): 1.4 s for a short answer, 3.9 s to answer about an image, 14.1 s for a 1,200-token prompt, 8.6 GB of RAM.
Known limits
- It reads and describes images, but it is weak at pointing to small interface elements by position (0 of 40 in our screen test). It was not trained on screenshots; the openTARS app clicks by accessibility names instead.
- Speech was only tested on short synthetic phrases; real voices, noise and long recordings are not measured yet. llama.cpp marks audio input as experimental.
- The text editor tasks and "look at this image file" tasks fail sometimes in our 80-task test.
- It can still get facts wrong. The openTARS app adds a warning and web checks for those cases.
Use
With llama.cpp:
llama-server -m gargantua-2.5-gemma4-e4b-Q4_K_M.gguf --mmproj mmproj-gargantua-2.5-gemma4-e4b-F16.gguf --jinja -c 8192
With Ollama:
ollama run ProjectOpenTARS/Gargantua-2.5:latest
Recommended sampling: temperature 0.4, top_p 0.95, top_k 64. The openTARS app sends think=false for this model.
Checksums
See SHA256SUMS.
- Downloads last month
- 169
4-bit