This Hugging Face model repository provides a 4-bit MLX quantization of Google's Gemma 3 12B instruction-tuned model. It is intended for developers and researchers who want to run the model locally on Apple silicon using MLX-compatible tooling.
Gemma 3 12b It is a Foundation models & chat project. It focuses on running the Gemma 3 12B instruction model locally with reduced memory usage on Apple silicon. It is built as an open-source project for developers and researchers running local language models. Gemma 3 12b It is open source under the Open Source license. It runs on the web and the command line, and it can be self-hosted.
Behind Gemma 3 12b It is mlx-community. It competes in a saturated segment with 23 similar projects in PulseGate's index. Key capabilities include 4-bit quantization, instruction tuning, and local inference.
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