Gemma 3 12b It Mlx 4Bit

🚀 przemekmroczek/gemma-3-12b-it-mlx-4Bit

This project provides a model converted to MLX format, which can be used for efficient machine learning tasks.

🚀 Quick Start

The Model przemekmroczek/gemma-3-12b-it-mlx-4Bit was converted to MLX format from unsloth/gemma-3-12b-it using mlx-lm version 0.22.1.

📦 Installation

pip install mlx-lm

💻 Usage Examples

Basic Usage

from mlx_lm import load, generate

model, tokenizer = load("przemekmroczek/gemma-3-12b-it-mlx-4Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

📄 License

The license of this model is gemma.