This is a quantized (AWQ INT4) version of Google's Gemma-4 12B instruction-tuned (it) model. It enables efficient local inference of a powerful 12-billion parameter language model on hardware with limited VRAM. The model is distributed on Hugging Face and compatible with Transformers and other inference frameworks.
Gemma 4 12B It Qat is a Foundation models & chat project. It focuses on running large instruction-tuned language models efficiently on consumer hardware. Gemma 4 12B It Qat is an open-source project aimed at developers. Gemma 4 12B It Qat is open source under the Open Source license. It runs on the web, the command line, and API.
cyankiwi builds and maintains Gemma 4 12B It Qat, and it first shipped in 2025. It competes in a saturated segment with 25 similar apps in PulseGate's index. Among its 4 catalogued features are Quantized Model, Instruction Tuned, and AWQ INT4. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do