Gargantua 2 Lite (0.8B)

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.

  • Base: Qwen3.5 0.8B (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-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).
  • Runs with: llama.cpp (llama-server), and with Ollama (ProjectOpenTARS/Gargantua-2:lite).

Measured results (openTARS test suites, local machine)

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.

Use

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.

Checksums

See SHA256SUMS. The GGUF file's SHA-256 matches the layer published on Ollama (8736bc95โ€ฆ).


Made by MastLLM, makers of openTARS. Other labs keep building bigger. We build small.

Downloads last month
223
GGUF
Model size
0.8B params
Architecture
qwen35
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Mast-LLM/Gargantua-2-Lite

Quantized
(436)
this model