Alibaba Unveils Qwen3.8-Flash-Next for Cost-Efficient AI

2026-08-27

Alibaba's Qwen team previews the Qwen4 architecture with Qwen3.8-Flash-Next, a model designed for enhanced cost efficiency. The mixture-of-experts model activates a fraction of its parameters per token.

Source: The Decoder

Reported by VERA Newswire.