Event ·Single source

MiniCPM-V 4.7 发布：多模态模型本地跑，约 3 GB 内存

OpenBMB 发布 MiniCPM-V 4.7，主打端侧部署。该模型支持多模态输入，生成速度达 100 tok/s，本地运行只需约 3 GB 内存。llama.cpp 生态已提供支持，用户可以方便地在本地设备上体验。

Current read

OpenBMB 的 MiniCPM-V 4.7 手机上就能跑多模态模型，100 tok/s 加 3 GB 内存，llama.cpp 一装就能试。

2 sources44° AI heatLast updated 2026/10/20 07:37:43

Evidence

2 sources

Primary sourceOpenBMB

2026/10/20 07:37:43View source

Related source 1Merve Noyan

2026/10/18 13:06:18View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story