Instructions to use beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj",
	filename="BgGPT-Gemma-3-27B-IT-V2-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj:Q4_K_M

Use Docker

docker model run hf.co/beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj:Q4_K_M

LM Studio
Jan

vLLM

How to use beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj:Q4_K_M

Ollama
How to use beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj with Ollama:
```
ollama run hf.co/beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj:Q4_K_M
```

Unsloth Studio

How to use beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj to start chatting

Atomic Chat new
Docker Model Runner
How to use beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj with Docker Model Runner:
```
docker model run hf.co/beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj:Q4_K_M
```

Lemonade

How to use beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj:Q4_K_M

Run and chat with the model

lemonade run user.BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj-Q4_K_M

List all available models

lemonade list

BgGPT Gemma 3 27B IT V2 GGUF Q4_K_M

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

BgGPT-Gemma-3-27B-IT-V2-Q4_K_M.gguf: text model quantized to Q4_K_M
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: Q4_K_M
Multimodal: yes, requires the included mmproj file

Example with llama.cpp

./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

Downloads last month: 309

GGUF

Model size

27B params

Architecture

gemma3

Hardware compatibility

4-bit

8-bit

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

Base model

INSAIT-Institute/BgGPT-Gemma-3-27B-IT

Quantized

(4)

this model

beleata74
/

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

BgGPT Gemma 3 27B IT V2 GGUF Q4_K_M

Contents

Note

Base model

Example with llama.cpp

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