Skip to content

docs: add community Apple Core AI conversion of MiniCPM5-1B #369

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
john-rocky wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs: add community Apple Core AI conversion of MiniCPM5-1B #369

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions README-cn.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -414,6 +414,10 @@ vllm serve ${model_path} \

</details>

#### 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。
Expand Down
4 changes: 4 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -412,6 +412,10 @@ vllm serve ${model_path} \

</details>

#### 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.
Expand Down