Qwen3

The Large Language Model (LLM), is entering the Next Level. In the early morning of Friday, Ali Tongyi team officially released and open-sourced the next-generation base model architecture Qwen3-Next. 80B of total parameters of the model is only activated 3B, the performance can be comparable to the flagship version of the Qianqian 3 235B model...

On September 5, Ali went live with the Preview version of Qwen3-Max, the strongest model in the Qwen3 series, which is also Ali's largest model to date, with more than 1 trillion participants. The model has now landed on the Ali Bailian platform, and is available for free on the Tongyi Thousand Questions app and Qwen Chat...

Early this morning, Alibaba open-sourced two new models of the Qwen3 series, Qwen3-Embedding and Qwen3-Reranker. These two models are designed for text representation, retrieval and sorting tasks, based on the Qwen3 base model training, fully inherited...

While everyone was guessing who would come first, DeepSeek V4 or R2 or Qwen3, Qwen3 was released. In the early morning of April 29, Alibaba open-sourced a new generation of Tongyi Qianqian Qwen3 series models, covering 8 different sizes. Among them, the flagship model Qwen3 2...