Gargantua 2 (2B)
Gargantua 2 is the main model of the openTARS assistant. It runs locally, opens programs, types, clicks, searches the web and runs commands, and it can look at a screenshot.
- Base: Qwen3.5 2B (Apache-2.0), fine-tuned by MastLLM for openTARS on its own tool-use, text-action and screen data, including code examples.
- Files:
gargantua-1.2-qwen3.5-2b-Q4_0.gguf(1.2 GB) and the vision projectormmproj-gargantua-qwen3.5-2b-Q8_0.gguf(0.36 GB). - Runs with: llama.cpp (
llama-server), and with Ollama (ProjectOpenTARS/Gargantua-2:latest).
Measured results (openTARS test suites, local machine, 9 Nov 2026)
These are our own tests, run with the openTARS app on an RTX 3050 6 GB. They are not public benchmarks.
| Test | Result |
|---|---|
| Text actions (rewrite, summarize, translate, ask about the text, ignore instructions hidden in it) | 76/76 |
| Tool-call choice (21 cases), time per request on the graphics card | 21/21, 0.4 s |
| Asked about people and things that do not exist, in the app | 16/16 say they do not know |
| Corrects a false premise in the question (plain model, 6 cases) | 4/6 |
Known limits: it can still get facts wrong (the app adds a warning and web checks for those cases) and it is weak at reading small text in screenshots.
Use
With llama.cpp:
llama-server -m gargantua-1.2-qwen3.5-2b-Q4_0.gguf --mmproj mmproj-gargantua-qwen3.5-2b-Q8_0.gguf -c 8192
With Ollama:
ollama run ProjectOpenTARS/Gargantua-2:latest
Recommended sampling: temperature 0.4, top_p 0.8, top_k 20, repeat_penalty 1.05. The openTARS app sends think=false for this model.
Checksums
See SHA256SUMS. The GGUF file's SHA-256 matches the layer published on Ollama (3f2d450e…).
Made by MastLLM, makers of openTARS. Other labs keep building bigger. We build small.