阿里发布Qwen4-Max,仅托管提供
Story overview
阿里巴巴发布Qwen4代首款模型Qwen4-Max,总参数2.4T、每token激活71B,支持文本、图像、视频输入和1M token上下文。该模型仅通过QwenCloud API、Token Plan、Qwen Studio、QwenWork和Qoder等托管渠道提供,不开源权重,因此无法自行部署或使用量化版本;默认限速为每分钟500万token。 据量子位报道,Qwen4-Max在CodeArena前端编程盲测中位列全球第6,Agents' Last Exam(ALE)取得46.7分;缓存命中每百万token低至0.5元,完成单任务的平均费用较上代模型下降6成。SiliconANGLE称,该模型主干配有3280亿N-gram参数充当缓存,采用四通道残差结构并带门控,注意力机制引入Gated DeltaNet与QSA以降低处理长提示词的硬件需求和基础设施成本。 关于开源,量子位称Qwen4系列中的中小尺寸模型将陆续开源发布;SiliconANGLE称阿里计划后续开源一批基于相同技术的较小模型,并开源Qwen-Live-Delivery-Plugin扩展,以提升Qwen4-Max执行耗时任务的能力。
AI-generated from reports · Updated 50m ago
Developments
2 developments
- Nov 17, 2026 05:21 · 1 reportsAlibaba launches Qwen4-Max with training and attention optimizationsSiliconANGLE · AI:Alibaba launches Qwen4-Max with training and attention optimizations
- Nov 16, 2026 15:51 · 2 reportsAlibaba releases Qwen4-Max, a 2.4T-parameter base model with native vision量子位 QbitAI:Alibaba releases Qwen4-Max, a 2.4T-parameter base model with native vision
Report timeline
Follow the reports to explore different perspectives.
- SiliconANGLE · AISelectedAlibaba launches Qwen4-Max with training and attention optimizations
Alibaba released Qwen4-Max, its newest flagship LLM, built on a Qwen4 architecture that made training more efficient. Its backbone has 2.4 trillion parameters but activates only 71 billion at a time, supported by 328 billion N-gram parameters acting as a cache. Alibaba says it used up to 35% fewer tokens than Qwen3.8-Max on an internal benchmark and 49% fewer on Terminal-Bench 4.0.
- MarkTechPostSelectedAlibaba's Qwen team releases Qwen4-Max, a 2.4T-parameter MoE model with 1M context
Alibaba's Qwen team released Qwen4-Max, the first Qwen4-generation model: a proprietary sparse MoE with a 2.4T-parameter backbone, 71B active per token and a 1M-token context window, accepting text, images and video. It is hosted only via QwenCloud, with no open weights. Alibaba cut API prices to $1.50/$4.50 per million input/output tokens and reports a 62% drop in average cost per task.
- 量子位 QbitAISelectedAlibaba releases Qwen4-Max, a 2.4T-parameter base model with native vision
Alibaba released Qwen4-Max on November 16, a base model with 2.4 trillion total parameters that activates 71B per token, native vision and million-token context. It uses a new MoE architecture built on Qwen sparse attention (QSA). It ranked sixth in the CodeArena front-end coding blind test and scored 46.7 on Agents' Last Exam. API access is live on the Qwen AI platform, with smaller Qwen4 models to be open-sourced.
Story activity trend
Not enough continuous observations to show a trend yet.