Alibaba· QwenNew model

Qwen3.5: Towards Native Multimodal Agents

Alibaba releases Qwen3.5, an open-weight native vision-language model with 397B total parameters (17B activated), featuring hybrid linear attention and sparse MoE architecture, a 1M token context window, and support for 201 languages.

From the source

We are delighted to announce the official release of Qwen3.5 , introducing the open-weight of the first model in the Qwen3.5 series, namely Qwen3.5-397B-A17B .

qwen.ai

Announced

15 Feb 2026 20:00 UTC

Detected

28 Aug 2026 13:23 UTC (+193d after)

Context window

1M context window