Skip to main content
← Back to news

Qwen3.8-2.4T-A95B: 2.4T open-weight parameters, 95B active

Model releases
Alibaba releases its first Qwen-Max-class model in open weight: 2.4T total parameters with 95B active, a 512-expert MoE (10 routed + 1 shared), Gated DeltaNet hybrid attention, and a native 262k-token context extendable to 1M.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.