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: Q8_0 (8-bit)
Format: GGUF
Size: ~4.13 GB (from the original ~8.5GB)
Parameters: 4.3B
Architecture: Gemma3
Context Window: 128K tokens
Language: Brazilian Portuguese
Converted by: Althayr Nazaret
GitHub

LinkedIn

HuggingFace

Usage

Ollama

bash

ollama pull https://huggingface.co/Althayr/Gemma-3-Gaia-PT-BR-4b-it-Q8_0-GGUF && \
ollama cp huggingface.co/Althayr/Gemma-3-Gaia-PT-BR-4b-it-Q8_0-GGUF Gemma-3-Gaia-PT-BR-4b-it-Q8_0 && \
ollama run Gemma-3-Gaia-PT-BR-4b-it-Q8_0

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-Q8_0-GGUF --hf-file gemma-3-gaia-pt-br-4b-it-q8_0.gguf -p "Me explique brevemente o que é inteligência artificial"

Server Execution

llama-server --hf-repo Althayr/Gemma-3-Gaia-PT-BR-4b-it-Q8_0-GGUF --hf-file gemma-3-gaia-pt-br-4b-it-q8_0.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:

bibtex

@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}}
}

Acknowledgments

If you use this specific GGUF version, please acknowledge:

Original model: CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it
GGUF conversion: Althayr/Gemma-3-Gaia-PT-BR-4b-it-Q8_0-GGUF

althayr/Gemma-3-Gaia-PT-BR-4b-it-Q8_0-GGUF

Gemma-3-Gaia-PT-BR-4b-it-Q8_0-GGUF

About GAIA