Qwen3.8-Flash-Next
Preview of the Qwen4 architecture: 125B mixture-of-experts (MoE) model with 6B active, plus 51B n-gram embeddings.
In this release we are opening the weights of Qwen3.8-Flash-Next, a multimodal MoE model that also serves as an early preview of the architecture used in Qwen4.
Official source
Qwen3.8-Flash-Next: A New Architecture, Towards Ultimate Cost-Efficiencyqwen.ai · published