This is a community-quantized 6-bit version of Google's Gemma-4 26B model optimized for the MLX framework on Apple devices. It is instruction-tuned (it) and includes a detailed chat template for interactive use. The model is designed for local inference with reduced memory footprint.
Gemma 4 26B A4B It sits in PulseGate's Quantised & converted weights category. It focuses on running large instruction-tuned models efficiently on Apple Silicon hardware. Gemma 4 26B A4B It is an open-source project aimed at developers using Apple Silicon. The project is open source (MIT). It runs on the web, the command line, and API.
It is developed by LM Studio Community, and it first shipped in 2024. The project is developed in the open on GitHub with 5.2k stars and 418 commits in the last 90 days. PulseGate's similarity index places it among 8 comparable projects. Among its 3 catalogued features are instruction tuning, 6-bit quantization, and MLX framework.
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