Skip to content
View original post on X: ModelScopeOfficial· Same story62/100AI score62/100

MiniCPM-V 4.7 is open-sourced on ModelScope as a 35B-A3B MoE multimodal model

AISummary

ModelScope says MiniCPM-V 4.7 is now open source under Apache 2.0, with a 35B-A3B MoE version and a 1B version. The post says it runs at 13+ tokens/s on iPhone 17 Pro Max and supports 4x/16x visual token compression. It lists FP8, GPTQ, AWQ, BNB, and GGUF variants that work with SGLang, vLLM, llama.cpp, Ollama, SWIFT, and LLaMA-Factory.

Post on XView on X
ModelScopeVerified on X
@ModelScope2022

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.

This story is featured in top picks: “OpenBMB releases MiniCPM-V 4.7, open-source multimodal models for on-device use”

Source: ModelScope · x.comPublished · added here

Topics

Multimodal AIOn-device AIOpen-source ecosystemModel releasesEvals & benchmarks