MiniCPM-V 4.7 联手 Nativ 实现苹果芯片端侧运行
OpenBMB 的 MiniCPM-V 4.7 现在能在 Mac 上离线跑多模态了,1B 版每秒 315 token,图像视频都能看,数据不出本地。
OpenBMB 与 Nativ 合作,让 MiniCPM-V 4.7 的 1B 和 35B-A3B 两个版本在 Mac 上实现 Day 0 端侧推理。基于 Nativ v0.4.x 的测试显示,1B 版解码速度达 315 tok/s,35B-A3B 版解码 90 tok/s。两个版本均支持图像和视频理解,数据完全保留在本地设备上。
🚀 MiniCPM-V 4.7 is now running on Apple Silicon! Thanks to our partnership with the @Nativ_AI, MiniCPM-V 4.7 (1B & 35B-A3B) now has Day 0 support for fully on-device inference on Mac.
With Nativ, you can run: 🧠 MiniCPM-V 4.7-35B-A3B — 35B capability with efficient inference ⚡ MiniCPM-V 4.7-1B — lightweight vision model for edge devices 📷 Image + video understanding 🔒 Fully local — your data stays on your device
Tested on Apple Silicon with Nativ v0.4.x: 1B: 24K+ prefill tokens/s, 315 tok/s decode 35B-A3B: 4K+ prefill tokens/s, 90 tok/s decode Bringing powerful multimodal models closer to everyday devices. 🍎 Huge thanks to the Nativ team for making this possible! 🔗 Nativ: https://t.co/rh21fTSYno