Alibaba's 2.4T Qwen3.8 Now Deployable on AWS

Alibaba's Qwen team released Qwen3.8-2.4T-A95B on August 12, 2026, the first open-weights Qwen-Max-class model. With 2.4 trillion total parameters, a hybrid linear-plus-full-attention architecture, and native 262K token context, it targets demanding agentic workloads including multi-step coding, long-horizon planning, and autonomous tool use. This guide details deploying the model on Amazon SageMaker HyperPod using vLLM on a ml.p6-b300 instance with 8 NVIDIA B300 Blackwell Ultra GPUs. Coverage includes NVFP4 quantization, built-in reasoning controls, tool calling, and native Multi-Token Prediction speculative decoding, taking the model from cluster provisioning to an OpenAI-compatible endpoint.