groxaxo/Huihui-gemma-4-26B-A4B-it-abliterated-GGUF

These are UD quantizations of huihui-ai/Huihui-gemma-4-26B-A4B-it-abliterated, packaged for llama.cpp / GGUF inference.

Quick Start

1. Download the latest release of llama.cpp.
2. Download your preferred model variant from the files below.
3. Use the corresponding mmproj file for multimodal inference.

Which version should I choose?

These variants are built using a Unsloths Amazing tensor distribution recipe to preserve as much quality as possible while reducing memory usage.

Notes

• This repo is a quantized release, of the finetuned version :
• Base model: huihui-ai/Huihui-gemma-4-26B-A4B-it-abliterated
• Runtime: llama.cpp