Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300 NVL72 | NVIDIA Technical Blog
Agentic AI / Generative AI Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300 NVL72 Aug 12, 2026 By Amr Elmeleegy , HJ Hang and Rajath Narasimha Discuss 0 Discuss 0 L T F R E Alibaba released the open weights for Qwen3.8-2.4T-A95B Qwen3.8-Max , its largest … …