QwenLaunchAI ModelsAugust 12, 2026

Qwen releases Qwen3.8-2.4T-A95B MoE model

Qwen released Qwen3.8-2.4T-A95B, a 2.4-trillion-parameter MoE model with 95B active parameters, along with an FP8 quantized version. The model is available on Hugging Face with support for Transformers, vLLM, and SGLang.

How this story unfolded

same day · 2 reports · 1 community post · 3 of 6 shown

  1. Aug 12
  2. Aug 13

Qwen by email

Get an email when Qwen has news

No news that day, no email.

More stories today

Open the live feed