Qwen3 is the latest generation of large language models in the Qwen series, offering a comprehensive suite of dense and mixture-of-experts models built upon extensive training. Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support. Qwen3-8B is an 8.2 billion parameter causal language model that uniquely supports seamless switching between thinking mode for complex logical reasoning, math, and coding, and non-thinking mode for efficient general-purpose dialogue within a single model. The model offers significantly enhanced reasoning capabilities that surpass previous QwQ and Qwen2.5 instruct models on mathematics, code generation, and commonsense logical reasoning. It features superior human preference alignment for creative writing, role-playing, multi-turn dialogues, and instruction following, along with expertise in agent capabilities for precise integration with external tools. The model supports over 100 languages and dialects with strong multilingual instruction following and translation capabilities. It natively supports a context length of 32,768 tokens and can handle up to 131,072 tokens with YaRN scaling techniques.