QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini.
Recent activity on QwQ 32B
Total usage per day on OpenRouter
Prompt
2.2M
Reasoning
1.62M
Completion
196K
Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.