Alibaba Releases Qwen3.8-Max: 2.4T Parameters and 1M Context

FellMentKE · x · 2026-08-06

Alibaba and the Qwen team have introduced Qwen3.8-Max, their most capable flagship model to date.

Architecture & Scale: Built on a cutting-edge Sparse MoE architecture, it features 2.4T total parameters but activates just 95B for massive efficiency.
Context & Modality: Natively multimodal across vision and text, it supports a 1M token context window, capable of processing massive inputs like 200+ page documents or 100-hour streams.
Agentic Capabilities: Designed for long-horizon task execution, it reportedly completed a 16-day real-world software engineering project independently and outperformed humans in the WWW2025 Multimodal Dialogue Intent Recognition Challenge.

More from Models