Qwen3-4B

Qwen3 4B Instruct 2507 by qwen

Updated version of Qwen3-4B non-thinking mode featuring significant improvements in general capabilities including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.

This model delivers substantial gains in long-tail knowledge coverage across multiple languages and markedly better alignment with user preferences in subjective and open-ended tasks, enabling more helpful responses and higher-quality text generation.

Enhanced capabilities in 256K long-context understanding.

Note: This model supports only non-thinking mode and does not generate <think></think> blocks in its output.