CoolFace
Modelpublic

beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj

sourceHugging Facegemmaupdated 6mo agoView on Hugging Face
2likes168downloads
Model Card

BgGPT Gemma 3 27B IT V2 GGUF Q4KM

This repository contains a GGUF export of a partially abliterated variant of BgGPT Gemma 3 27B IT.

Contents

  • —BgGPT-Gemma-3-27B-IT-V2-Q4_K_M.gguf: text model quantized to Q4KM
  • —mmproj-out-bggpt27b-full-uncensor-v2-F16.gguf: multimodal projector for image support

Note

This model is partially abliterated. The intervention targets refusal behavior in the language model, so outputs can differ from the original instruct model, especially on sensitive topics.

Base model

  • —Base: INSAIT-Institute/BgGPT-Gemma-3-27B-IT
  • —Format: GGUF
  • —Quantization: Q4KM
  • —Multimodal: yes, requires the included mmproj file

Example with llama.cpp

bash
./llama-mtmd-cli   -m BgGPT-Gemma-3-27B-IT-V2-Q4_K_M.gguf   --mmproj mmproj-out-bggpt27b-full-uncensor-v2-F16.gguf   --image your_image.jpg   -p "What is shown in this image?"   -dev CUDA0 -ngl all