OpenBMB· @OpenBMB · X·· 3 小时前AI 评分60
AI 导读
面壁智能 MiniCPM-V 4.7 已在 ModelScope 开源，是 35B-A3B 的 MoE 多模态模型，采用 Apache 2.0 协议。官方称其可在 iPhone 17 Pro Max 上以 13+ tokens/s 流畅运行端侧无损推理，Instruct 模式下整体得分高于 Qwen3.6 35B-A3B 且推理时间更短；支持 4x/16x 视觉 token 压缩，提供 35B-A3B 和 1B 两种规格及 FP8、GPTQ、AWQ、BNB、GGUF 变体，兼容 SGLang、vLLM、llama.cpp、Ollama、SWIFT 和 LLaMA-Factory，可运行于 iOS、Android 和 HarmonyOS，并支持 Rockchip、Houmo、Intel、AMD、Arm 的 day-0 适配。
正文
Great to see MiniCPM-V 4.7 on ModelScope! 🚀
Thanks for the support 💙 Excited to make powerful on-device multimodal AI accessible to even more developers!
MiniCPM-V 4.7 is now open source on ModelScope: a 35B-A3B MoE multimodal model built to run on-device without compromising performance. Apache 2.0. 🤖 https://modelscope.ai/collections/OpenBMB/MiniCPM-V-47 📱 First open-source MoE with smooth, lossless on-device inference, running at 13+ tokens/s on iPhone 17 Pro Max. 🔥 New Pareto frontier: in Instruct mode, it reaches a higher overall score in less inference time than Qwen3.6 35B-A3B. ⚡ Mixed 4x/16x visual token compression lets developers balance visual detail and inference cost per task. 🛠️ Two sizes (35B-A3B and 1B) with FP8, GPTQ, AWQ, BNB, and GGUF variants. Works with SGLang, vLLM, llama.cpp, Ollama, SWIFT, and LLaMA-Factory. 💻 Runs on iOS, Android, and HarmonyOS, with day-0 support for Rockchip, Houmo, Intel, AMD, and Arm.在 X 查看被引用的帖子
来源：OpenBMB · x.com