From d0b5e2145963be604cd5945bf80e8c3642d011e5 Mon Sep 17 00:00:00 2001 From: john-rocky Date: Sat, 5 Sep 2026 05:08:19 +0900 Subject: [PATCH] docs: add community Apple Core AI conversion of MiniCPM5-1B --- README-cn.md | 4 ++++ README.md | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/README-cn.md b/README-cn.md index a8f681b..88941fb 100644 --- a/README-cn.md +++ b/README-cn.md @@ -414,6 +414,10 @@ vllm serve ${model_path} \ +#### Apple Core AI（社区） + +MiniCPM5-1B 的 Apple [Core AI](https://developer.apple.com/documentation/coreai) `.aimodel` 社区转换版本（iOS 27 / macOS 27）见 [MiniCPM5-1B-CoreAI](https://huggingface.co/mlboydaisuke/MiniCPM5-1B-CoreAI)：int8，1.0 GB，iPhone 17 Pro 上解码 66.8 tok/s，在基准提示上与 HF fp32 参考逐 token 一致；Swift 用法见模型卡。 + ### 桌宠 我们同步发布了 **[OpenBMB/MiniCPM-Desk-Pet](https://github.com/OpenBMB/MiniCPM-Desk-Pet)**，一个由 MiniCPM5-1B 本地驱动的桌宠应用。它通过轻量 `llama.cpp` `llama-server` sidecar 加载 GGUF 模型，并向 Electron 桌宠 UI 提供 OpenAI 兼容的本地接口。 diff --git a/README.md b/README.md index 9baa9b7..9cb0cba 100644 --- a/README.md +++ b/README.md @@ -412,6 +412,10 @@ vllm serve ${model_path} \ +#### Apple Core AI (community) + +A community conversion of MiniCPM5-1B to Apple's [Core AI](https://developer.apple.com/documentation/coreai) `.aimodel` format (iOS 27 / macOS 27) is available at [MiniCPM5-1B-CoreAI](https://huggingface.co/mlboydaisuke/MiniCPM5-1B-CoreAI): int8, 1.0 GB, 66.8 tok/s decode on iPhone 17 Pro, token-exact against the HF fp32 reference on the benchmark prompts; the Swift recipe is in the card. + ### Desktop Pet We also ship **[OpenBMB/MiniCPM-Desk-Pet](https://github.com/OpenBMB/MiniCPM-Desk-Pet)**, a desktop pet driven locally by MiniCPM5-1B. It uses a thin `llama.cpp` `llama-server` sidecar to load the GGUF model and serves an OpenAI-compatible local endpoint to an Electron pet UI.