aitwinkle/gemma-3-4b-t1-it-gguf repository overview

⁠Overview

🌏 Website⁠ | 🎮 Discord⁠ | 😺 GitHub⁠ | 🤗 Hugging Face⁠ | 🔗 Linkedin⁠

This model is a GGUF-packaged Gemma 3 4B instruction-tuned model, further fine-tuned with data reflecting Taiwanese social and cultural context, published using Docker Model Runner.
It can be pulled and executed directly via Docker without manually managing model files or runtimes.

⁠Requirements

• Docker Desktop (latest recommended)
• Docker Model Runner enabled
  • Docker Desktop → Settings → AI / Model Runner

Verify Model Runner is running:

docker model status

⁠Pull the Model

Download the model from Docker Hub:

docker model pull aitwinkle/gemma-3-4b-t1-it-gguf:latest

Verify the model is available locally:

docker model list

⁠Run the Model

Run the model with a single prompt:

docker model run aitwinkle/gemma-3-4b-t1-it-gguf:latest "Hello! Please introduce yourself."

The model will generate a response directly in your terminal.

⁠Interactive Mode

Start an interactive session:

docker model run -i aitwinkle/gemma-3-4b-t1-it-gguf:latest

Then enter prompts interactively:

> Summarize the purpose of instruction-tuned language models.

Exit the session with Ctrl+D.

⁠Notes

• This model is packaged from a GGUF file and runs via Docker Model Runner.
• No manual model download or runtime configuration is required.
• Inference performance depends on local hardware and Docker settings.