Brocker Blog

Independent AI, software, infrastructure, and security news with verified primary sources and original editorial context — not a headline aggregator. Written for engineers and industry readers.

Home Contact Technology News

Search

1 result for “GB300 NVL72”

NVIDIA Publishes Day-0 Inference Results for Qwen3.8-2.4T-A95B on GB300 NVL72
Technology 15 Aug 2026

NVIDIA Publishes Day-0 Inference Results for Qwen3.8-2.4T-A95B on GB300 NVL72

NVIDIA published Day-0 inference results for Alibaba's Qwen3.8-2.4T-A95B on its GB300 NVL72 rack, hitting over 4,000 tokens per second per GPU in FP8. The 2.4-trillion-parameter MoE model activates only 95 billion parameters per token and ships with configurable reasoning depth.

Quick Links

  • About Us
  • Privacy Policy
  • Cookie Policy
  • Terms of Service
  • Contact
  • Editorial Policy
  • Corrections Policy
  • RSS Feed

Topics

  • Technology
  • News

Social

Twitter GitHub

© 2026 Brocker.Org. All rights reserved.

AI news with verified sources and original editorial context.

We use cookies to improve your experience.