Instructions to use solarkyle/pixellock-gemma-12b-pixelart-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 solarkyle/pixellock-gemma-12b-pixelart-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 solarkyle/pixellock-gemma-12b-pixelart-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf solarkyle/pixellock-gemma-12b-pixelart-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 solarkyle/pixellock-gemma-12b-pixelart-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf solarkyle/pixellock-gemma-12b-pixelart-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 solarkyle/pixellock-gemma-12b-pixelart-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf solarkyle/pixellock-gemma-12b-pixelart-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 solarkyle/pixellock-gemma-12b-pixelart-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf solarkyle/pixellock-gemma-12b-pixelart-gguf:Q4_K_M

Use Docker

docker model run hf.co/solarkyle/pixellock-gemma-12b-pixelart-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use solarkyle/pixellock-gemma-12b-pixelart-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "solarkyle/pixellock-gemma-12b-pixelart-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": "solarkyle/pixellock-gemma-12b-pixelart-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/solarkyle/pixellock-gemma-12b-pixelart-gguf:Q4_K_M

Ollama
How to use solarkyle/pixellock-gemma-12b-pixelart-gguf with Ollama:
```
ollama run hf.co/solarkyle/pixellock-gemma-12b-pixelart-gguf:Q4_K_M
```
Unsloth Desktop

How to use solarkyle/pixellock-gemma-12b-pixelart-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf solarkyle/pixellock-gemma-12b-pixelart-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": "solarkyle/pixellock-gemma-12b-pixelart-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use solarkyle/pixellock-gemma-12b-pixelart-gguf with Docker Model Runner:
```
docker model run hf.co/solarkyle/pixellock-gemma-12b-pixelart-gguf:Q4_K_M
```

Lemonade

How to use solarkyle/pixellock-gemma-12b-pixelart-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull solarkyle/pixellock-gemma-12b-pixelart-gguf:Q4_K_M

Run and chat with the model

lemonade run user.pixellock-gemma-12b-pixelart-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use solarkyle/pixellock-gemma-12b-pixelart-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 solarkyle/pixellock-gemma-12b-pixelart-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 solarkyle/pixellock-gemma-12b-pixelart-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use solarkyle/pixellock-gemma-12b-pixelart-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf solarkyle/pixellock-gemma-12b-pixelart-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 "solarkyle/pixellock-gemma-12b-pixelart-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"

PixelLock — Gemma-4-12B Pixel-Art Retexturer (GGUF, q4_k_m)

A QLoRA fine-tune of google/gemma-4-12b-it for footprint-locked pixel-art retexturing.

It is a text LLM, not an image generator. A sprite is serialized to a palette-indexed text grid (a PALETTE block plus a GRID of space-separated cells). The model rewrites that grid in a new style, and a per-sprite GBNF decoding grammar (llama.cpp) forces every transparent cell to stay transparent — so the exact silhouette and transparency are preserved by construction, not by luck.

What it does

Retheme / restyle palette-indexed pixel-art sprites (best at 16-64px) to any vibe (lava, ice, gold, cosmic, ...) - pixel-perfect.
2x upscale with added shading (each input pixel becomes a 2x2 block).

How to use

Run with llama.cpp and pass a footprint-derived GBNF grammar per sprite. The sprite is sent as a PALETTE + GRID wire block; the grammar pins every transparent cell. See the PixelLock app for the wire format and grammar builder.

Training

Supervised fine-tune (QLoRA, rank 64, alpha 64, lr 1e-4, completion-only loss) on a curated corpus of palette-indexed pixel-art sprites (<=64px), with step-checkpointing + best-eval selection and a held-out eval set. Final eval loss ~0.38.

Files

pixellock-gemma-12b-q4_k_m.gguf - q4_k_m quant for llama.cpp / LM Studio / Ollama.

Built for the Build Small hackathon.

Downloads last month: 54

GGUF

Model size

12B params

Architecture

gemma4

Hardware compatibility

4-bit

solarkyle
/

pixellock-gemma-12b-pixelart-gguf

PixelLock — Gemma-4-12B Pixel-Art Retexturer (GGUF, q4_k_m)

What it does

How to use

Training

Files

Spaces using solarkyle/pixellock-gemma-12b-pixelart-gguf 2