面壁发布 MiniCPM-V 4.7 模型，在 iPhone 18 Pro Max 上实现了 20.51 tokens/sec 的平均解码速度。该版本通过 Lookahead Expert Scheduling、优化专家加载、细粒度量化和 DSpark 投机解码等技术提升了端侧多模态推理性能。
35B multimodal AI. Running locally on an iPhone. Now at over 20 tokens/sec. 🚀
MiniCPM-V 4.7 achieves 20.51 tokens/sec average decoding speed on iPhone 18 Pro Max (12GB) — a 6.07× speedup over the same device’s unoptimized SSD expert-loading baseline.
⚡ Behind the speed: Lookahead Expert Scheduling (LES), optimized expert loading, fine-grained quantization, and DSpark speculative decoding.
📱 Watch the new on-device demo below. Powerful multimodal AI, right in your pocket.
Try it 👇
🔗 GitHub: http://github.com/OpenBMB/MiniCPM-V
🤗 Hugging Face: http://huggingface.co/collections/openbmb/minicpm-v-47
LES: https://github.com/tc-mb/llama.cpp-omni/blob/master/docs/les/lookahead-expert-scheduling.md
#MiniCPM #OpenBMB
来源：OpenBMB · x.com