The QwQ reasoning model is significantly leaner than DeepSeek R1 and is said to be more powerful in many areas.

While DeepSeek-R1 operates with 671 billion parameters, QwQ-32B achieves comparable performance with a much smaller footprint.

B, a compact reasoning model built on its latest large language model (LLM), Qwen2.5-32b, one it says delivers performance comparable to other large cutting edge models, including Chinese rival DeepSeek and OpenAI’s o1,