Qwen3 4B Thinking 2507 by qwen

Updated thinking version of Qwen3-4B featuring continued scaling of thinking capability, improving both the quality and depth of reasoning. Qwen3-4B-Thinking-2507 includes the following key enhancements:

Significantly improved performance on reasoning tasks, including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human expertise. Markedly better general capabilities, such as instruction following, tool usage, text generation, and alignment with human preferences. Enhanced 256K long-context understanding capabilities.

Supports a context length of up to 262,144 tokens.

Note: This model supports only thinking mode. Specifying enable_thinking=True is not required.