This repository provides a 5-bit quantized GGUF-style or MLX-optimized version of Google's Gemma 4 12B Instruct model. It is designed for efficient local execution on Apple devices using the MLX framework. The model is instruction-tuned and suitable for chat and reasoning tasks.
Gemma 4 12B It sits in PulseGate's Foundation models & chat category. It focuses on running the latest Gemma 4 instruction model efficiently on Apple Silicon hardware. Gemma 4 12B It is an open-source project aimed at developers. The project is open source (MIT). Gemma 4 12B It is available on the command line.
Behind Gemma 4 12B It is lmstudio-community, and it first shipped in 2024. The project is developed in the open on GitHub with 5.3k stars and 528 commits in the last 90 days. PulseGate's similarity index places it among 16 comparable projects. Among its 3 catalogued features are 5-bit quantization, MLX framework, 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