This model is a 4-bit quantized version of Google's Gemma 3 27B instruction-tuned model, converted to MLX format for efficient inference on Apple Silicon. It is a multimodal model capable of processing both images and text, allowing it to answer questions about images and perform vision-language tasks. The model maintains the capabilities of the original Gemma 3 instruction-tuned variant while being optimized for performance on MLX-compatible hardware through quantization.