Instructions to use marcelone/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 marcelone/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="marcelone/Gemma-3-Gaia-PT-BR-4b-it-gguf",
	filename="Gemma-3-Gaia-PT-BR-4b-it-gguf-bf16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use marcelone/Gemma-3-Gaia-PT-BR-4b-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 marcelone/Gemma-3-Gaia-PT-BR-4b-it-gguf:BF16
# Run inference directly in the terminal:
llama-cli -hf marcelone/Gemma-3-Gaia-PT-BR-4b-it-gguf:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf marcelone/Gemma-3-Gaia-PT-BR-4b-it-gguf:BF16
# Run inference directly in the terminal:
llama-cli -hf marcelone/Gemma-3-Gaia-PT-BR-4b-it-gguf:BF16

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 marcelone/Gemma-3-Gaia-PT-BR-4b-it-gguf:BF16
# Run inference directly in the terminal:
./llama-cli -hf marcelone/Gemma-3-Gaia-PT-BR-4b-it-gguf:BF16

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 marcelone/Gemma-3-Gaia-PT-BR-4b-it-gguf:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf marcelone/Gemma-3-Gaia-PT-BR-4b-it-gguf:BF16

Use Docker

docker model run hf.co/marcelone/Gemma-3-Gaia-PT-BR-4b-it-gguf:BF16

LM Studio
Jan
Ollama
How to use marcelone/Gemma-3-Gaia-PT-BR-4b-it-gguf with Ollama:
```
ollama run hf.co/marcelone/Gemma-3-Gaia-PT-BR-4b-it-gguf:BF16
```

Unsloth Studio

How to use marcelone/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 marcelone/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 marcelone/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 marcelone/Gemma-3-Gaia-PT-BR-4b-it-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use marcelone/Gemma-3-Gaia-PT-BR-4b-it-gguf with Docker Model Runner:
```
docker model run hf.co/marcelone/Gemma-3-Gaia-PT-BR-4b-it-gguf:BF16
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull marcelone/Gemma-3-Gaia-PT-BR-4b-it-gguf:BF16

Run and chat with the model

lemonade run user.Gemma-3-Gaia-PT-BR-4b-it-gguf-BF16

List all available models

lemonade list

This model is based on the Gemma3 architecture (4 billion parameters) and has been quantized using a mixed-precision approach to balance memory efficiency and inference speed while preserving accuracy.

Quantization Types Used:

Q8_0-MiXED Full precision (float32): 205 tensors 8-bit quantization (q8_0): 47 tensors 3-bit quantization (q3_K): 48 tensors 4-bit quantization (q4_K): 47 tensors 5-bit quantization (q5_K): 49 tensors 6-bit quantization (q6_K): 48 tensors Model Size: Approximately 2.33 GiB Average Bits Per Weight (BPW): 5.16