OpenBMB· @OpenBMB · X·· 4 小时前AI 评分62
AI 导读
@techNmak 用面壁 MiniCPM-V 4.7 35B-A3B 实验构建了一个 Neo-Brutalist 风格的作品集 UI，OpenBMB 转发致谢并期待其后续作品。该模型总参数 35B、每次仅激活 3B，在 iPad Pro M4（16GB）上达 17+ tokens/s、iPhone 17 Pro Max 上达 13+ tokens/s，优化移动端设置下内存占用约 3GB；另有面向 OCR、图表、数学和通用理解的 1B 紧凑版本，两个版本均支持 256K 上下文窗口，权重、推理代码和微调代码开源，GitHub 与 Hugging Face 可获取。
正文 · 原文
Great to see community experiments with MiniCPM-V 4.7! Thanks @techNmak for sharing your neo-brutalist portfolio UI. Curious to see what you build next!
Spent some time experimenting with MiniCPM-V4.7 35B-A3B and built this Neo-Brutalist portfolio UI, featuring bold colors, chunky layouts, and a slightly unconventional visual style. What makes this experiment interesting is the model behind it. OpenBMB’s MiniCPM-V 4.7 is pushing multimodal AI toward more practical deployment on everyday hardware. With 35B total parameters but only 3B activated at a time, MiniCPM-V 4.7 35B-A3B delivers 17+ tokens/s on iPad Pro M4 (16GB) and 13+ tokens/s on iPhone 17 Pro Max, using just ~3GB of memory in its optimized mobile setup. 🤯 There’s also a compact 1B variant designed for tasks like OCR, chart, math, and general understanding. Both variants support a 256K context window, and the model weights, inference code, and fine-tuning code are open source. For me, the interesting part of multimodal AI is its potential to work with visual information beyond text, and to make those capabilities more accessible through efficient, flexible deployment. Explore MiniCPM-V 4.7 from @OpenBMB: GitHub：http://github.com/OpenBMB/MiniCPM-V Hugging Face：http://huggingface.co/collections/openbmb/minicpm-v-47在 X 查看被引用的帖子
来源：OpenBMB · x.com