Qwen3 30B A3B 2507

Updated version of Qwen3-30B-A3B featuring significant improvements in general capabilities including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.

This MoE model uses 3.3B activated parameters from 128 total experts with 8 active at any time. Compared to the original Qwen3-30B-A3B, it delivers substantial gains in long-tail knowledge coverage across multiple languages and markedly better alignment with user preferences in subjective and open-ended tasks.

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

Advanced agent capabilities and support for over 100 languages and dialects.

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