This is an 8-bit quantized version of Google's Gemma-4 12B instruction-tuned model, optimized for the MLX framework on Apple Silicon. It allows efficient local inference on Macs and is distributed via Hugging Face for use with MLX and compatible tools.
In the Foundation models & chat space, Gemma 4 12B It takes a focused approach. It focuses on running large Gemma models efficiently on Apple Silicon hardware. It is built as an open-source project for developers. The project is open source (MIT). It ships for the web, the command line, and API.
Behind Gemma 4 12B It is lmstudio-community, based in the United States, and it first shipped in 2024. Development happens publicly on GitHub with 5.3k stars and 496 commits in the last 90 days. PulseGate's similarity index places it among 13 comparable projects. Among its 4 catalogued features are MLX Optimized, 8-bit Quantization, and Instruction Tuned. 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