Everyday AI Express, February 16 — Alibaba Qianwen officially released Qwen3.5 and launched the open-weight version of the first model in the Qwen3.5 series, Qwen3.5-397B-A17B. This model adopts an innovative hybrid architecture that combines linear attention (Gated Delta Networks) with sparse mixture of experts (MoE), achieving excellent inference efficiency: a total of 397 billion parameters, with only 17 billion parameters activated per forward pass, optimizing speed and cost while maintaining capability.
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
Alibaba officially releases the new generation large model Qwen3.5
Everyday AI Express, February 16 — Alibaba Qianwen officially released Qwen3.5 and launched the open-weight version of the first model in the Qwen3.5 series, Qwen3.5-397B-A17B. This model adopts an innovative hybrid architecture that combines linear attention (Gated Delta Networks) with sparse mixture of experts (MoE), achieving excellent inference efficiency: a total of 397 billion parameters, with only 17 billion parameters activated per forward pass, optimizing speed and cost while maintaining capability.