OpenBMB releases MiniCPM-V 4.7-35B-A3B multimodal model

OpenBMB released MiniCPM-V 4.7-35B-A3B, the first MoE model in the MiniCPM-V series, enabling smooth on-device inference at over 13 tokens/s on iPhone 17 Pro Max and advancing the performance-efficiency Pareto frontier beyond Qwen3.6 35B-A3B.

• MiniCPM-V 4.7 runs 35B multimodal model on phone2026-10-15
• OpenBMB runs 35B MoE model locally on iPhone2026-10-21
• User claims merging Qwen3.6 and 3.8 27B boosts generation efficiency2026-09-29