Gargantua 2 Lite is the small model of the openTARS assistant. It is built to run on the CPU, on machines without a graphics card. It opens programs, types, searches the web, runs commands, and can look at a screenshot.
gargantua-1.2-lite-qwen3.5-0.8b-Q4_0.gguf (0.5 GB) and the vision projector mmproj-gargantua-qwen3.5-0.8b-Q8_0.gguf (0.12 GB).llama-server), and with Ollama (ProjectOpenTARS/Gargantua-2:lite).These are our own tests, run with the openTARS app. They are not public benchmarks.
| Test | Result |
|---|---|
| Tool-call choice (21 cases) | 21/21 |
| Text actions (rewrite, summarize, translate, ask about a text) | 67/76 |
| Invented facts, app mode (48 questions, fewer is better) | 9 errors |
Portable suite (opentars --prova, 48 tasks) |
45/48 |
Known limits: it can still get facts wrong, and it is weaker at reading screenshots. Use the 2B model when the machine has a graphics card.
With llama.cpp:
llama-server -m gargantua-1.2-lite-qwen3.5-0.8b-Q4_0.gguf --mmproj mmproj-gargantua-qwen3.5-0.8b-Q8_0.gguf -c 8192
With Ollama:
ollama run ProjectOpenTARS/Gargantua-2:lite
Recommended sampling: temperature 0.4, top_p 0.8, top_k 20, repeat_penalty 1.05.
See SHA256SUMS. The GGUF file's SHA-256 matches the layer published on Ollama (8736bc95…).
Made by MastLLM, makers of openTARS. Other labs keep building bigger. We build small.
Qwen/Qwen3.5-0.8B