面壁智能发布 MiniCPM-V 4.7：35B MoE 多模态模型可在手机 3GB 内存运行
🎬 35B MoE multimodal AI. On your phone. With just 3GB of memory. 🤯
面壁智能发布 MiniCPM-V 4.7，这是一个 35B-A3B 的 MoE 多模态模型，可在手机上以仅 3GB 内存运行，能识别现实路牌、按约束做规划、解析复杂文档并对视觉数据推理。模型由 LES（Lookahead Expert Scheduling）支持，将高效 MoE 推理带到移动设备，同时提供轻量 1B 版本用于资源受限硬件；开发者还可用 Self-Replay Fine-Tuning（SRFT）为新任务定制模型并保持通用性能，覆盖 iOS 与 Android。
推荐理由
精选AI 评分 65
面壁智能公布 MiniCPM-V 4.7 在手机端以 3GB 内存运行 35B MoE 多模态模型，并给出 LES 调度与 SRFT 微调两项配套技术。
主题
正文
当前显示原文，中文全文译文尚未就绪。
🎬 35B MoE multimodal AI. On your phone. With just 3GB of memory. 🤯
This is MiniCPM-V 4.7 in action: reading real-world signs, planning around constraints, parsing complex documents, and reasoning over visual data.
Powered by LES (Lookahead Expert Scheduling), the 35B-A3B model brings efficient MoE inference to mobile devices, while the lightweight 1B variant delivers capable multimodal understanding on resource-constrained hardware.
🛠️ With Self-Replay Fine-Tuning (SRFT), developers can customize models for new tasks while maintaining general performance.
From iOS to Android, MiniCPM-V 4.7 makes powerful multimodal AI more practical to run locally.