Alibaba releases Qwen3.8-2.4T-A95B weights
Alibaba Opens Qwen3.8-2.4T-A95B Weights as First Qwen-Max-Class MoE
First open-source MoE model matching Qwen-Max performance, offering developers enterprise-grade capabilities without cost.
Alibaba's Qwen team published open weights for Qwen3.8-2.4T-A95B, a 2.4-trillion-parameter MoE model with 95 billion active parameters. The model features hybrid attention and long context capabilities designed for agentic workloads. The release includes same-period SageMaker HyperPod and vLLM recipes for deployment.
Alibaba Opens Qwen3.8-2.4T-A95B Weights as First Qwen-Max-Class MoE
Alibaba's Qwen team published open weights for Qwen3.8-2.4T-A95B, a 2.4-trillion-parameter MoE with 95 billion active parameters. Hybrid attention and long context target agentic workloads, with same-period SageMaker HyperPod and vLLM recipes.
