Qwen3-4B-AWQ is a 4 billion parameter quantized language model that represents the latest generation in the Qwen series. It is a quantized version of Qwen3-4B using 4-bit AWQ quantization, offering a compact yet capable model for efficient deployment. The model features a unique dual-mode capability that allows seamless switching between a thinking mode for complex logical reasoning, mathematics, and coding tasks, and a non-thinking mode for efficient general-purpose dialogue. This flexibility enables users to optimize performance across different types of queries within a single model. Qwen3-4B-AWQ supports 100+ languages and dialects with strong multilingual instruction-following capabilities. The model natively supports context lengths of 32,768 tokens and can be extended to 131,072 tokens using the YaRN scaling technique. It excels in reasoning, instruction following, agent capabilities with tool use, creative writing, role-playing, and multi-turn conversations.