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 projector mmproj-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 (3f2d450eโ€ฆ).


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

Downloads last month
118
GGUF
Model size
2B 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

Finetuned
Qwen/Qwen3.5-2B
Quantized
(343)
this model