Qwen3 235B A22B Thinking 2507

Enhanced version of Qwen3-235B-A22B featuring significant improvements in thinking and reasoning capabilities with state-of-the-art performance among open-source thinking models.

This MoE model uses 22B activated parameters from 128 total experts with 8 active at any time. Features dramatically improved performance on reasoning tasks including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human expertise.

Supports a context length of up to 262,144 tokens natively with enhanced long-context understanding.

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