阿里开放 Qwen3.8-2.4T-A95B 权重，2.4T 参数、单 token 激活 95B
Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300 NVL72
阿里开放了 Qwen3.8-2.4T-A95B（Qwen3.8-Max）的模型权重，这是其目前最大的开放权重模型。该模型总参数 2.4T、单 token 激活 95B，采用细粒度 MoE 架构，混合全注意力与线性注意力，上下文窗口最高 100 万 token。NVIDIA 开发者博客介绍在 GB300 NVL72 上部署该模型并支持可配置推理。
摘要给出 Qwen3.8-2.4T-A95B 的开放权重与关键规格，读者可借此了解其 MoE 结构与长上下文配置。
Alibaba released the open weights for Qwen3.8-2.4T-A95B (Qwen3.8-Max), its largest open-weight model, bringing near-frontier capabilities to the open...
Alibaba released the open weights for Qwen3.8-2.4T-A95B (Qwen3.8-Max), its largest open-weight model, bringing near-frontier capabilities to the open ecosystem. It has 2.4T total parameters with 95B activated per token. It’s a fine-grained mixture of experts (MoE) architecture with a hybrid of full and linear attention, a context window of up to one million tokens, and an output length of up to…
来源：NVIDIA Developer Blog · developer.nvidia.com