Alibaba’s Qwen Team Releases QwQ-32B Open-Source Reasoning Model, Said to Perform Similar to DeepSeek-R1

Alibaba’s Qwen Team, a division tasked with growing synthetic intelligence (AI) fashions, launched the QwQ-32B AI mannequin on Wednesday. It is a reasoning mannequin primarily based on prolonged check time compute with seen chain-of-thought (CoT). The builders declare that regardless of being smaller in dimension in contrast to the DeepSeek-R1, the mannequin can match its efficiency primarily based on benchmark scores. Like different AI fashions launched by the Qwen Team, the QwQ-32B can also be an open-source AI mannequin, nonetheless, it isn’t absolutely open-sourced.

QwQ-32B Reasoning AI Model Released

In a weblog submit, Alibaba’s Qwen Team detailed the QwQ-32B reasoning mannequin. QwQ (quick for Qwen with Questions) sequence AI fashions had been first launched by the corporate in November 2024. These reasoning fashions had been designed to provide an open-source different for the likes of OpenAI’s o1 sequence. The QwQ-32B is a 32 billion parameter mannequin developed by scaling reinforcement studying (RL) strategies.

Explaining the coaching course of, the builders stated that the RL scaling strategy was added to a cold-start checkpoint. Initially, RL was used just for coding and mathematics-related duties, and the responses had been verified to guarantee accuracy. Later the method was used for normal capabilities together with rule-based verifiers. The Qwen Team discovered that this methodology elevated normal capabilities of the mannequin with out lowering its math and coding efficiency.

QwQ-32B AI Model benchmarks
Photo Credit: Alibaba

The builders declare that these coaching constructions enabled the QwQ-32B to carry out at related ranges to the DeepSeek-R1 regardless of the latter being a 671-billion-parameter mannequin (with 37 billion activated). Based on inside testing, the crew claimed that QwQ-32B outperforms DeepSeek-R1 within the LiveBench (coding), IFEval (chat or instruction fine-tuned language), and the Berkeley Function Calling Leaderboard V3 or BFCL (potential to name capabilities) benchmarks.

Developers and AI fanatics can discover the open weights of the mannequin on Hugging Face itemizing and Modelscope. The mannequin is accessible underneath the Apache 2.0 licence which permits tutorial and research-related utilization however forbids industrial use circumstances. Additionally, for the reason that full coaching particulars and datasets usually are not obtainable, the mannequin can also be not replicable or might be deconstructed. DeepSeek-R1 was additionally obtainable underneath the identical licence.

In case one lacks the best {hardware} to run the AI mannequin regionally, they will additionally entry its capabilities by way of Qwen Chat. The mannequin picker menu on the top-left of the web page will let customers choose the QwQ-32B-preview mannequin.