An INT4 AWQ quantized version of Google's Gemma 3 12B instruction-tuned (it) model. It is published on Hugging Face for efficient local or self-hosted inference. The quantization enables the model to run on more accessible hardware while preserving most of its reasoning capabilities.
Gemma 3 12b It is a Foundation models & chat project. It focuses on deploying a capable 12B parameter instruction-tuned model with reduced memory requirements. Gemma 3 12b It is an open-source project aimed at developers. The project is open source (Apache-2.0). It runs on the web, the command line, and API.
It is developed by gaunernst, and it first shipped in 2018. The project is developed in the open on GitHub with 36k stars and 1.9k commits in the last 90 days. The category is crowded — PulseGate's index counts 25 comparable projects. Among its 3 catalogued features are INT4 Quantization, AWQ, and Instruction Tuned.
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