Alibaba unveiled Qwen4-Max, a 2.4T-parameter base model with 71B activated parameters built on a new QSA-based MoE architecture, featuring native vision and million-token context. It cuts average cost per task by 58% versus its predecessor, ranks sixth globally in the CodeArena front-end blind test, and is now available via API on the Qwen AI platform, with smaller variants to be open-sourced.
Qwen Sparse Attention
Qwen 稀疏注意力
Efficient attention mechanism used in Qwen4-Max that sparsifies computation over long contexts to cut inference cost.
Curated Intelligence
Alibaba unveiled Qwen4-Max, a 2.4T-parameter base model with 71B activated parameters built on a new MoE architecture with Qwen Sparse Attention, native vision and million-token context. It ranks 6th globally on the CodeArena front-end coding blind test, scores 46.7 on Agents' Last Exam, cuts cost per task by 58% versus its predecessor, and has produced real results in materials and drug discovery.
Alibaba unveiled its next-generation foundation model family Qwen4, launching the flagship Qwen4-Max first on the Qianwen AI platform with API and Token Plan access. Built on a new MoE architecture with Qwen Sparse Attention (QSA), the model carries 2.4T total parameters, native vision and million-token context, lifting Terminal-Bench 4.0 from 37.9 to 48.5 while cutting per-task tokens by nearly 50% and average cost by 58%. Alibaba also detailed real deployments in automotive production-line engineering and AI4S materials discovery.