阿里巴巴发布 Qwen3.8-Flash，多模态 MoE 模型，性能强，成本低，是 Qwen4 架构的早期预览，值得尝试！
Qwen3.8-Flash 多模态 MoE 模型发布，参数达 125B，成本效率高，性能优异，支持 262K 原生上下文，即将通过 QwenCloud API 提供，价格为 0.16/1M 输入令牌和 0.47/1M 输出令牌。新架构 GDN + QSA 混合注意力，训练成本降低至 Qwen3.7-Plus 的 1/9，在编码和办公任务上表现突出。
⚡Meet Qwen3.8-Flash, a multimodal MoE and an early preview of the Qwen4 architecture, now open-weigh...
⚡Meet Qwen3.8-Flash, a multimodal MoE and an early preview of the Qwen4 architecture, now open-weight! The production version Qwen3.8-Flash will be available soon via QwenCloud API at just $ 0.16/1M input tokens and $ 0.47/1M output tokens. 125B parameters + 51B N-gram embeddings, with just 6B activated per token. Unmatched cost-efficiency. What's new: 🥳 - Next architecture: GDN + QSA hybrid attention, Gated Residual, N-gram Embedding & Muon optimizer, serving as a precursor to the architecture used in Qwen4. - Dramatically lower training and inference costs: trained at just 1/9 the cost of Qwen3.7-Plus, while outperforming it across the board with especially strong gains in coding and office tasks. - Strong performance: scoring 58.7 on DeepSWE 1.1, 62.5 on SWE-bench Pro, 73.9 on CoWorkBench, 84.5 on AndroidWorld, and 95.7 on MathVision (with CI). - 262K native context, extensible to 1M with YaRN. We’re also releasing the weights for Qwen3.8-Flash-Next, giving the community an early look at the new architecture we’re exploring for Qwen4.🚀 We can't wait to see what you build with Qwen3.8-Flash!👀👇 - Bl qwen.ai/blog?id=qwen3.… FLgJ - Technical Repo github.com/QwenLM/Qwen3.8… IkQO - Hugging Fa huggingface.co/Qwen/Qwen3.8-F… AABt - ModelSco modelscope.cn/models/Qwen/Qw… NuFG 💬 34 🔄 79 ❤️ 352 👀 9719 📊 103 ⚡