This model is a 4-bit quantized version of LiquidAI/LFM2.5-1.2B-Thinking converted to MLX format for efficient inference on edge devices. It is a 1.2 billion parameter language model capable of text generation across multiple languages including English, Arabic, Chinese, French, German, Japanese, Korean, and Spanish. The model features thinking capabilities and is optimized for running on Apple Silicon and other edge hardware through the MLX framework.