MastLLM

non-profit
Activity Feed

AI & ML interests

Sub-1B parameters models. Other Labs keep bulding bigger, we build small.

Recent Activity

MastLLM  updated a model about 2 hours ago
Mast-LLM/Gargantua-2.5-Lite
MastLLM  updated a model about 2 hours ago
Mast-LLM/Gargantua-2.5
MastLLM  updated a model about 2 hours ago
Mast-LLM/Gargantua-Pro
View all activity

Organization Card

MastLLM

Other labs keep building bigger. We build small. MastLLM makes compact, open AI models that run on the hardware you already own, and the apps that put them to work. The Mast family of sub-1B models is coming soon.

openTARS, our flagship

openTARS is an open source AI assistant that runs on your own computer. Ask in your own words: it opens programs, clicks buttons by their name, types, searches the web, runs commands and looks at your screen. By default nothing leaves your machine, and there is no account or subscription. It runs on Linux, Windows and macOS.

openTARS models

Built on Gemma 4: Gargantua 2.5 (E4B) and Gargantua Lite Gen 3 (E2B) power openTARS 5.3, with vision and audio.

The models are GGUF files with SHA-256 checksums. Every model card lists the tests we ran and the known limits. They are our own tests on one machine, not public benchmarks.

Get openTARS

MastLLM, makers of openTARS. The openTARS code is MIT. Each model keeps the license of its base: Gemma 4 (Apache-2.0), Qwen2.5-Coder (Apache-2.0) and FunctionGemma (Gemma terms). Contact: projectopentars@gmail.com

datasets 0

None public yet