Dev Radar
Support
LiveUpdated 2026-10-30 21:12 UTC

📱 35B parameters. Real-time inference. On a phone.

📱 35B parameters. Real-time inference. On a phone. Meet Lookahead Expert Scheduling (LES), the inference system…

This is a dev post classified by AGK Intelligence as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.

📱 35B parameters. Real-time inference. On a phone. Meet Lookahead Expert Scheduling (LES), the inference system powering MiniCPM-V 4.7’s 35B-A3B MoE model on edge devices. 🚀 On an iPhone 18 Pro Max, the full system reaches 20.51 tokens per second, a 6.07× speedup over loading expert weights on demand. How? Three coordinated optimizations: - 🔮 Scheduling: Predict and prefetch the next layer’s experts while the current layer computes. - 💾 Storage: Combine contiguous expert layouts with mixed-precision quantization to reduce loading overhead. - ⚡ Compute: Use DSpark speculative decoding to ver

Posted by OpenBMB (13.1k followers) 2 days ago · 185 likes · 6.9k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: llama.cpp-omni, minicpm-v.

More dev work like this

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 21:12 UTC. Full method.