Alleged Alibaba Qwen3.8-Max Specs Leak: 2.4T Parameters and 1M Context

The Qwen team revealed that the upcoming Qwen3.8-Max will feature 2.4 trillion total parameters with a sparse MoE architecture, activating only 95B during inference. The flagship model also reportedly supports a 1 million token context window.

2026-08-05 ~ 2026-08-05 · 3 related posts

• Alibaba's Qwen3.8-Max Leaks: 2.4T Parameters and 1M Context — Aiden_Tech_Ai · 2026-08-05
• Alibaba's Qwen 3.8-Max Activates Only 95B of 2.4T Parameters — Div_pradeep · 2026-08-05
• Qwen Devs AMA: 3.8 Model Hits 2.4T Params, 27B Version Coming Soon — pmttyji · 2026-08-05