Instructions to use althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF",
	filename="Gemma-3-Gaia-PT-BR-4b-it.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF
# Run inference directly in the terminal:
llama cli -hf althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF
# Run inference directly in the terminal:
llama cli -hf althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF

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 althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF
# Run inference directly in the terminal:
./llama-cli -hf althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF

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 althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF

Use Docker

docker model run hf.co/althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF

LM Studio
Jan

vLLM

How to use althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "althayr/Gemma-3-Gaia-PT-BR-4b-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": "althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF

Ollama
How to use althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF with Ollama:
```
ollama run hf.co/althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF
```

Unsloth Studio

How to use althayr/Gemma-3-Gaia-PT-BR-4b-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 althayr/Gemma-3-Gaia-PT-BR-4b-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 althayr/Gemma-3-Gaia-PT-BR-4b-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 althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF with Docker Model Runner:
```
docker model run hf.co/althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF
```

Lemonade

How to use althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF

Run and chat with the model

lemonade run user.Gemma-3-Gaia-PT-BR-4b-it-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Gemma-3-Gaia-PT-BR-4b-it-GGUF

This model was converted to GGUF format from CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it using llama.cpp.

About GAIA

GAIA is an open, state-of-the-art language model for Brazilian Portuguese. It was developed by continuously pre-training the google/gemma-3-4b-pt model on an extensive, high-quality corpus of Portuguese data. The goal of GAIA is to democratize access to cutting-edge AI technology in Brazil.

Original Model Developed by

Brazilian Association of AI (ABRIA)
Center of Excellence in Artificial Intelligence (CEIA-UFG)
Nama
Amadeus AI
Google DeepMind

Model Details

Base Model: CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it
Original Model: google/gemma-3-4b-pt
Quantization: BF16 (default)
Format: GGUF
Size: ~8.5GB
Parameters: 4.3B
Architecture: Gemma3
Context Window: 128K tokens
Language: Brazilian Portuguese
Converted by: Althayr Nazaret

Usage

Ollama

ollama pull https://huggingface.co/Althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF && \
ollama cp huggingface.co/Althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF Gemma-3-Gaia-PT-BR-4b-it-GGUF && \
ollama run Gemma-3-Gaia-PT-BR-4b-it-GGUF

llama.cpp

Installation

Follow the OS specific instructions at llama.cpp

CLI Execution

llama-cli --hf-repo Althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF --hf-file gemma-3-gaia-pt-br-4b-it.gguf -p "Me explique brevemente o que é inteligência artificial"

Server Execution

llama-server --hf-repo Althayr/Gemma-3-Gaia-PT-BR-4b-it-GGUF --hf-file gemma-3-gaia-pt-br-4b-it.gguf -c 2048

Capabilities

The model is optimized for Brazilian Portuguese tasks, including:

💬 Conversation - Chatbots and virtual assistants
❓ Question Answering - Factual question responses
📝 Summarization - Summarizing long texts
✍️ Text Generation - Creative content creation
🎯 Sentiment Analysis - Emotion analysis in text
🔍 Text Understanding - Document interpretation

License and Terms

This model is provided under and subject to the Gemma Terms of Use. By downloading or using this model, you agree to be bound by these terms.

Key obligations include:

Compliance with the Gemma Prohibited Use Policy.
Providing a copy of the Gemma Terms of Use to any third-party recipients.
Prominent notice that this is a modified (quantized) version.

Citation

If you use this model in research or applications, please cite the original GAIA paper:

@misc{gaia-gemma-3-4b-2025,
  title={GAIA: An Open Language Model for Brazilian Portuguese},
  author={CAMILO-JUNIOR, C. G.; OLIVEIRA, S. S. T.; PEREIRA, L. A.; AMADEUS, M.; FAZZIONI, D.; NOVAIS, A. M. A.; JORDÃO, S. A. A.},
  year={2025},
  publisher={Hugging Face},
  journal={Hugging Face repository},
  howpublished={\url{https://huggingface.co/CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it}}
}