This is Llama 3.2 1B Instruct converted to 4-bit quantized format optimized for use with the MLX framework. The model is based on Meta's Llama 3.2 1B parameter foundational large language model, fine-tuned with instruction-following capabilities to follow user directions and engage in multi-turn conversations. It supports multiple languages including English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. This quantized version reduces model size while maintaining performance, making it suitable for deployment on Apple Silicon and other resource-constrained environments through the MLX machine learning framework.