Instructions to use ddh0/gemma-4-it-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ddh0/gemma-4-it-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ddh0/gemma-4-it-GGUF",
	filename="gemma-4-12B-it-Q8_0.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 ddh0/gemma-4-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 ddh0/gemma-4-it-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf ddh0/gemma-4-it-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ddh0/gemma-4-it-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf ddh0/gemma-4-it-GGUF:Q8_0

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 ddh0/gemma-4-it-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf ddh0/gemma-4-it-GGUF:Q8_0

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 ddh0/gemma-4-it-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ddh0/gemma-4-it-GGUF:Q8_0

Use Docker

docker model run hf.co/ddh0/gemma-4-it-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use ddh0/gemma-4-it-GGUF with Ollama:
```
ollama run hf.co/ddh0/gemma-4-it-GGUF:Q8_0
```

Unsloth Studio

How to use ddh0/gemma-4-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 ddh0/gemma-4-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 ddh0/gemma-4-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 ddh0/gemma-4-it-GGUF to start chatting

How to use ddh0/gemma-4-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 ddh0/gemma-4-it-GGUF:Q8_0

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": "ddh0/gemma-4-it-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ddh0/gemma-4-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 ddh0/gemma-4-it-GGUF:Q8_0

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 ddh0/gemma-4-it-GGUF:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use ddh0/gemma-4-it-GGUF with Docker Model Runner:
```
docker model run hf.co/ddh0/gemma-4-it-GGUF:Q8_0
```

Lemonade

How to use ddh0/gemma-4-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ddh0/gemma-4-it-GGUF:Q8_0

Run and chat with the model

lemonade run user.gemma-4-it-GGUF-Q8_0

List all available models

lemonade list

These are miscellaneous GGUF quantizations of the instruct-tuned Gemma 4 series of models, released by Google.

For more information about Gemma, you should refer to the original model cards.

The chat template baked into these GGUFs is technically outdated, however, inference in llama.cpp should still work exactly as it should, thanks to these fixes:

llama.cpp#21704: common : better align to the updated official gemma4 template
llama.cpp#21760: common/gemma4 : handle parsing edge cases

For the latest official chat template, refer to the original model repo.

Downloads last month: 25,830

GGUF

Model size

12B params

Architecture

gemma4

Hardware compatibility

8-bit

16-bit

32-bit

View +17 variants

Inference Providers NEW

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

Model tree for ddh0/gemma-4-it-GGUF

Base model

google/gemma-4-26B-A4B

Finetuned

google/gemma-4-26B-A4B-it

Quantized

(231)

this model