OpenBMB 宣布 MiniCPM-V 4.7 在 iPhone 18 Pro Max（12GB）上实现平均 20.51 tokens/sec 的本地解码速度，较未优化的 SSD 专家加载基线提速 6.07×。提速来自 Lookahead Expert Scheduling（LES）、优化专家加载、细粒度量化与 DSpark 投机解码，GitHub 和 Hugging Face 已提供下载。
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