TMTPOST — Tongyi Qwen has officially open-sourced its latest AI coding model, Qwen3-Coder, marking a significant step in advancing open AI development. The release includes the most powerful version to date: the Qwen3-Coder-480B-A35B-Instruct model. The model is a Mixture-of-Experts (MoE) architecture with 480 billion total parameters, of which 35 billion are activated during inference. It natively supports 256K context length, with the ability to scale up to 1 million tokensusing YaRN extension technology.