This is a community or official variant of Google's Gemma 4 12B instruction-tuned (it) model with QAT (Quantization-Aware Training) and Q4_0 quantization options. It includes an advanced chat template supporting tool calling and structured output. The model can be used with Transformers for local inference on consumer hardware.
In the Foundation models & chat space, Gemma 4 12B It Qat Q4 0 Unquantized Assistant takes a focused approach. It focuses on running large instruction-tuned language models locally with reduced memory footprint via quantization. It is built as an open-source project for developers. The project is open source (Open Source). Gemma 4 12B It Qat Q4 0 Unquantized Assistant is available on the web, the command line, and API.
Behind Gemma 4 12B It Qat Q4 0 Unquantized Assistant is Google. The category is crowded — PulseGate's index counts 25 comparable projects. Among its 3 catalogued features are Instruction Tuned, Tool Calling, and Chat Template.
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