阿里发布 Qwen3.8-Flash-Next 权重，预览 Qwen4 架构
Experiment with Qwen3.8-Flash-Next on NVIDIA GB300 NVL72 for Agentic Coding
阿里发布 Qwen3.8-Flash-Next 的模型权重，作为即将推出的 Qwen4 架构预览，供开发者实验和评估。该模型为多模态 MoE 架构，主模型 125B 参数，另有 51B N-gram 嵌入向量，每 token 激活 6B 参数，原生上下文窗口 262,144 token，可扩展至 1M token。
阿里放出 Qwen3.8-Flash-Next 权重作为 Qwen4 架构预览，读者可据此了解其 MoE 结构与上下文规格。
Alibaba released the model weights for Qwen3.8-Flash-Next as a preview of the upcoming Qwen4 architecture for developers to experiment with and evaluate. It’s...
Alibaba released the model weights for Qwen3.8-Flash-Next as a preview of the upcoming Qwen4 architecture for developers to experiment with and evaluate. It’s a multimodal mixture-of-experts (MoE) model with a 125B-parameter main model supplemented by an additional 51B N-gram embeddings, with 6B parameters activated per token. It has a native 262,144-token context window, extensible to 1M tokens…
来源：NVIDIA Developer Blog · developer.nvidia.com