QwQ-32B
https://qwenlm.github.io/blog/qwq-32bQwQ-32B: Embracing the Power of Reinforcement Learning | Qwen
https://huggingface.co/Qwen/QwQ-32BQwen/QwQ-32B
https://modelscope.cn/models/Qwen/QwQ-32Bmodel scope
https://huggingface.co/spaces/Qwen/QwQ-32B-DemoQwen/QwQ-32B-Demo
https://chat.qwen.ai/Qwen Chat
https://gyazo.com/0c8ca1aeae923c3a44f27dd3fad7ed95
≒DeepSeek-R1みたいな感じ