Model Releases

vLLM provides Day-0 support for Qwen3.8-2.4T-A95B

Original title:Day 0 Support for Qwen3.8-2.4T-A95B on vLLM

AI summary

vLLM announced Day-0 support for Qwen3.8-2.4T-A95B, a 2.4-trillion-parameter sparse MoE model based on the Qwen 3.5 architecture, with 512 experts. In its 92-layer hybrid backbone, every fourth layer uses full attention while the remaining 69 layers use linear attention.

Key Takeaways

  • vLLM announced Day-0 support for Qwen3.
  • 4T-A95B,a 2.
  • 4-trillion-parameter sparse MoE model based on the Qwen 3.
  • 5 architecture,with 512 experts.
  • In its 92-layer hybrid backbone,every fourth layer uses full attention while the remaining 69…

Quick Facts

Published
Updated
Source
vLLM 官方博客(RSS)
Category
Model Releases
AI score
72
Read the original Read the full article at the original source
Why it matters

原文给出架构细节、量化方案和硬件要求,读者可以据此评估部署这个 2.4T 参数开源权重模型的成本与配置。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: vLLM provides Day-0 support for Qwen3.8-2.4T-A95B. August 12, 2026. https://new.nat6.net/en/news/cmtym20dd000erovumyee3pp4/

View all →