Qwen's New 2.4T MoE Model Tops Hugging Face Trending

Qwen · hf · 2026-08-12

Alibaba's latest Qwen model, Qwen/Qwen3.8-2.4T-A95B, has surged to the top of the Hugging Face trending list.

The model utilizes a Mixture-of-Experts (MoE) architecture with a massive total parameter count of 2.4T and 95B active parameters. It supports text-generation pipelines, is endpoints compatible, and is designed for conversational and text generation tasks.

Related event: Alibaba Releases Qwen3.8-2.4T-A95B Model(7 posts)→

Original post →

More from Models

Models channel →