Instructions to use LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-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 LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-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 LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-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 LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-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 LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-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 LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-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": "LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-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/LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF:Q4_K_M

Ollama
How to use LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF with Ollama:
```
ollama run hf.co/LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF:Q4_K_M
```
Unsloth Desktop

How to use LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-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": "LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF:Q4_K_M
```

Lemonade

How to use LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-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 LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-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 LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-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 "LyraNovaHeart/AuriAetherwiing_G4-26B-A4B-Musica-v1-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"

Sillytavern/koboldcpp

by Milten20 - opened Jul 7

Discussion

Milten20

Jul 7

I can't set this model correctly using above. It's super unstable, replies are full of emoji and other nonsensical things no matter if I use text or chat completion. I use Q8 quant.

LyraNovaHeart

Owner Jul 7

Hey,

Sorry about that! You may consider using Q6_K, sometimes Q8 does weird things to models. Other things you can try is correcting your template, as Gemma is VERY sensitive to it's template. I did notice odd behavior before, and I'm unsure what the root cause other than the template is.

You may also consider using quants by Mradermancher or Bartowski, also, you can try Marinara Engine, which tends to have much better chat completions and doesn't freak out with Gemma 4.

Milten20

Jul 7

Thank you for help! What template this model uses? Because I found several Gemma4 templates already

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment