mlboydaisuke
/

MiniCPM5-2B-CoreAI

@@ -96,6 +96,8 @@ Gated on an iPhone 17 Pro (iOS 27.0) against the fp32 HF oracle: teacher-forced
 method, 512-token prompt, 1024 generated, 5 trials, two back-to-back runs): decode **48.0 / 38.2 tok/s**, prefill 1858 / 1494 tok/s; footprint 2.0 GB. The Neural Engine is the power-efficient lane; these are
 not a GPU comparison (different protocol from the `int8/` row above).
 ## Measured
 | | decode | prefill | numerics | size |

 method, 512-token prompt, 1024 generated, 5 trials, two back-to-back runs): decode **48.0 / 38.2 tok/s**, prefill 1858 / 1494 tok/s; footprint 2.0 GB. The Neural Engine is the power-efficient lane; these are
 not a GPU comparison (different protocol from the `int8/` row above).
+Same-day interleaved A/B on the same phone (one app embedding both bundles, 128-token prompt, 256 generated, 5 trials, ANE-GPU-ANE-GPU): Neural Engine 4-bit **55.4 / 51.5 tok/s** decode (1954 / 1793 prefill) vs this repo's `int8/` GPU bundle **22.8 / 20.6** (894 / 715) — 2.4× decode, but the ANE bundle also reads half the weight bytes per token, so this is what-ships vs what-ships, not equal precision; GPU cold specialization 18.4 s vs ANE AOT load 0.2 s.
 ## Measured
 | | decode | prefill | numerics | size |