Alibaba just released Qwen3.8-Flash: “An early preview of the architecture in Qwen4”

Alibaba has released Qwen3.8-Flash, a 125-billion-parameter multimodal Mixture-of-Experts AI model serving as an early preview of the architecture planned for Qwen4. This model introduces architectural innovations like hybrid Gated DeltaNet and Gated Attention to improve efficiency and capability, and is positioned as a cost-effective solution for coding and office tasks.