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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use bombman/gemma-4-12B-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 bombman/gemma-4-12B-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bombman/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 serve -hf bombman/gemma-4-12B-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bombman/gemma-4-12B-it-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf bombman/gemma-4-12B-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf bombman/gemma-4-12B-it-GGUF:Q4_K_M

Use Docker

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

Llama new
LM Studio
Jan
Ollama
How to use bombman/gemma-4-12B-it-GGUF with Ollama:
```
ollama run hf.co/bombman/gemma-4-12B-it-GGUF:Q4_K_M
```
Unsloth Desktop

How to use bombman/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 serve -hf bombman/gemma-4-12B-it-GGUF:Q4_K_M

Configure the model in Pi

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

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bombman/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

Hermes Agent

How to use bombman/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 serve -hf bombman/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 bombman/gemma-4-12B-it-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use bombman/gemma-4-12B-it-GGUF with OpenClaw:

Start the llama.cpp server

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

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "bombman/gemma-4-12B-it-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Gemma 4 12B IT GGUF

GGUF quantizations of Google's Gemma 4 12B IT model.

Optimized for local inference with:

Ollama
LM Studio
Jan AI
llama.cpp
Open WebUI
Text Generation WebUI
KoboldCpp

Downloads

Quant	Recommended Use
Q4_K_S	Smallest size
Q4_K_M	⭐ Recommended
Q8_0	Maximum quality
F16	Further quantization

Quick Start

Ollama

Create a file named Modelfile

FROM ./gemma-4-12B-it-Q4_K_M.gguf

PARAMETER temperature 0.7
PARAMETER num_ctx 32768

SYSTEM You are a helpful AI assistant.

Create model:

ollama create gemma4-12b -f Modelfile

Run:

ollama run gemma4-12b

LM Studio

Download a GGUF file.
Open LM Studio.
Import the model.
Load the model.
Start chatting.

Recommended:

gemma-4-12B-it-Q4_K_M.gguf

Jan AI

Download a GGUF file.
Open Jan AI.
Models → Import Model
Select the GGUF file.
Start chatting.

Recommended:

gemma-4-12B-it-Q4_K_M.gguf

Open WebUI

Using Ollama:

ollama create gemma4-12b -f Modelfile

Then select:

gemma4-12b

inside Open WebUI.

llama.cpp

Run:

./build/bin/llama-cli \
  -m gemma-4-12B-it-Q4_K_M.gguf \
  -cnv

Server:

./build/bin/llama-server \
  -m gemma-4-12B-it-Q4_K_M.gguf

OpenAI-compatible endpoint:

http://localhost:8080/v1

Hardware Recommendations

Quant	RAM
Q4_K_S	10 GB+
Q4_K_M	12 GB+
Q8_0	18 GB+
F16	32 GB+

Which Version Should I Download?

Most Users

Q4_K_M

Best balance of:

Quality
Speed
Memory usage

Highest Quality

Q8_0

Smallest Size

Q4_K_S

Further Quantization

F16

Credits

Google for Gemma 4
ggml-org for llama.cpp
Ollama
LM Studio
Jan AI
Open WebUI

Disclaimer

This repository contains GGUF conversions only.

All original model weights and intellectual property belong to Google.

Downloads last month: 320

GGUF

Model size

12B params

Architecture

gemma4

Hardware compatibility

4-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

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

Base model

google/gemma-4-12B

Finetuned

google/gemma-4-12B-it

Quantized

(406)

this model