Instructions to use INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF",
	filename="BgGPT-Gemma-3-12B-IT-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

llama.cpp

How to use INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF: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 INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF: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 INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF:Q4_K_M

Use Docker

docker model run hf.co/INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF",
		"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/INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF:Q4_K_M

Ollama
How to use INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF with Ollama:
```
ollama run hf.co/INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF:Q4_K_M
```

Unsloth Studio new

How to use INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF 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 INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF 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 INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF to start chatting

Docker Model Runner
How to use INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF with Docker Model Runner:
```
docker model run hf.co/INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF:Q4_K_M
```

Lemonade

How to use INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.BgGPT-Gemma-3-12B-IT-GGUF-Q4_K_M

List all available models

lemonade list

BgGPT-Gemma-3-12B-IT-GGUF

GGUF quantized versions of BgGPT-Gemma-3-12B-IT for use with llama.cpp, Ollama, LM Studio, and other GGUF-compatible tools. BgGPT 3.0 is a series of Bulgarian-adapted LLMs based on Gemma 3, developed by INSAIT.

Blog post: BgGPT-3 Release

Key improvements over BgGPT 2.0

Vision-language understanding — The models understand both text and images within the same context.
Instruction-following — Trained on a broader range of tasks, multi-turn conversations, complex instructions, and system prompts.
Longer context — Effective context of 131k tokens for longer conversations and complex instructions.
Updated knowledge cut-off — Pretraining data up to May 2025, instruction fine-tuning up to October 2025.

Available quantizations

Filename	Quant type	Description
`BgGPT-Gemma-3-12B-IT-Q4_K_M.gguf`	Q4_K_M	Good balance of quality and size — recommended
`BgGPT-Gemma-3-12B-IT-Q5_K_M.gguf`	Q5_K_M	High quality, slightly larger
`BgGPT-Gemma-3-12B-IT-Q6_K.gguf`	Q6_K	Very high quality, near lossless
`BgGPT-Gemma-3-12B-IT-Q8_0.gguf`	Q8_0	Essentially lossless

Usage

llama.cpp

# Download a specific quantization
huggingface-cli download INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF \
    --include "BgGPT-Gemma-3-12B-IT-Q4_K_M.gguf" \
    --local-dir .

# Run with llama-cli
llama-cli -m BgGPT-Gemma-3-12B-IT-Q4_K_M.gguf \
    -p "Кога е основан Софийският университет?" \
    -n 512

Ollama

Create a Modelfile:

FROM ./BgGPT-Gemma-3-12B-IT-Q4_K_M.gguf

Then:

ollama create bggpt-gemma3-12b -f Modelfile
ollama run bggpt-gemma3-12b

LM Studio

Search for BgGPT-Gemma-3-12B-IT-GGUF in the model browser, or download a GGUF file manually and load it.

Download

# Download all quantizations
huggingface-cli download INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF

# Download a specific file
huggingface-cli download INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF \
    --include "BgGPT-Gemma-3-12B-IT-Q4_K_M.gguf" \
    --local-dir .

License

BgGPT-Gemma-3-12B-IT-GGUF is distributed under the Gemma Terms of Use.

Downloads last month: 258

GGUF

Model size

12B params

Architecture

gemma3

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Model tree for INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF

Base model

INSAIT-Institute/BgGPT-Gemma-3-12B-IT

Quantized

(2)

this model

Collection including INSAIT-Institute/BgGPT-Gemma-3-12B-IT-GGUF

BgGPT-Gemma-3

Collection

9 items • Updated Mar 26 • 7