Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300 NVL72 – NVIDIA Developer

NVIDIA has published guidance on deploying Alibaba’s Qwen3.8-2.4T-A95B model, a 2.4 trillion-parameter large language model, on its GB300 NVL72 GPU infrastructure with configurable reasoning capabilities. The announcement demonstrates support for running extremely large-scale models on NVIDIA’s latest accelerator hardware architecture. The deployment solution enables configurable inference reasoning features for the ultra-large parameter model.

Read Full Article →