Alibaba Launches Qwen3.8-Max: 2.4T Parameter MoE with Native Multimodal

alifcoder · x · 2026-08-09

Alibaba has released Qwen3.8-Max, its most powerful flagship model to date. Built on a Sparse Mixture-of-Experts (MoE) architecture, the model features a total of 2.4T parameters with 95B active parameters.

Key Highlights:

Qwen3.8-Max is now available globally via Alibaba Cloud Model Studio API, with open weights scheduled for release on Hugging Face next week.

Related event: Rumors Claim Alibaba Released Qwen3.8-Max(2 posts)→

Original post →

More from Models

Models channel →