Model card: all four models, per-folder licences (Apache 2.0 and LFM 1.0), sources, tags and the TestFlight link
081e944 verified | license: other | |
| license_name: apache-2.0-and-lfm1.0 | |
| license_link: https://huggingface.co/publicarray/fieldnote-models#licences | |
| base_model: | |
| - openbmb/MiniCPM5-1B | |
| - openbmb/MiniCPM5-2B | |
| - Qwen/Qwen3.5-2B | |
| - LiquidAI/LFM2.5-1.2B-Instruct | |
| base_model_relation: quantized | |
| pipeline_tag: text-generation | |
| library_name: coreai | |
| tags: | |
| - core-ai | |
| - coreai | |
| - apple | |
| - ios | |
| - iphone | |
| - on-device | |
| - neural-engine | |
| - minicpm5 | |
| - qwen3.5 | |
| - lfm2.5 | |
| # Fieldnote models | |
| Small language models compiled ahead of time for Apple's Core AI, one ready-to-load | |
| bundle per iPhone chip family. Used by [Fieldnote](https://github.com/array-ai/fieldnotes), | |
| an on-device meeting recorder, to write meeting notes on the phone. A phone with a | |
| matching chip downloads a compiled bundle instead of compiling the model itself, | |
| which ran an iPhone 16 out of memory for the larger models. | |
| **Try Fieldnote:** [join the TestFlight beta](https://testflight.apple.com/join/c2M82CMX) | |
| (iPhone 15 Pro or later, iOS 27). | |
| ## Bundles | |
| | Folder | Model | Chip | Phones | Licence | | |
| |---|---|---|---|---| | |
| | `ios-h17g` | MiniCPM5 1B | h17g | iPhone 16 family | Apache 2.0 | | |
| | `ios-h17p` | MiniCPM5 1B | h17p | iPhone 16 family | Apache 2.0 | | |
| | `ios-h18p` | MiniCPM5 1B | h18p | iPhone 17 Pro | Apache 2.0 | | |
| | `minicpm5-2b/ios-h17p` | MiniCPM5 2B | h17p | iPhone 16 family | Apache 2.0 | | |
| | `minicpm5-2b/ios-h18p` | MiniCPM5 2B | h18p | iPhone 17 Pro | Apache 2.0 | | |
| | `qwen3.5-2b/ios-h17p` | Qwen3.5 2B | h17p | iPhone 16 family | Apache 2.0 | | |
| | `qwen3.5-2b/ios-h18p` | Qwen3.5 2B | h18p | iPhone 17 Pro | Apache 2.0 | | |
| | `lfm2.5-1.2b/ios-h17p` | LFM2.5 1.2B Instruct | h17p | iPhone 16 family | LFM Open License 1.0 | | |
| | `lfm2.5-1.2b/ios-h18p` | LFM2.5 1.2B Instruct | h18p | iPhone 17 Pro | LFM Open License 1.0 | | |
| Each folder is a complete bundle: `metadata.json` (pointing at the compiled model), | |
| `tokenizer/`, and the compiled `.aimodelc`. A phone needs only the folder whose chip | |
| matches `AIModel.deviceArchitectureName`. Other devices should use the portable | |
| export (below) and let Core AI compile it. | |
| ## Sources | |
| Every bundle is a portable Core AI export compiled for one chip. No weights were | |
| changed. | |
| | Model | Original | Portable Core AI export, pinned revision | | |
| |---|---|---| | |
| | MiniCPM5 1B | [openbmb/MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B) | [mlboydaisuke/MiniCPM5-1B-CoreAI](https://huggingface.co/mlboydaisuke/MiniCPM5-1B-CoreAI) `ios-static/` @ `f38d143ec50cb2e54d8388479b919e3b9283943b` | | |
| | MiniCPM5 2B | [openbmb/MiniCPM5-2B](https://huggingface.co/openbmb/MiniCPM5-2B) | [mlboydaisuke/MiniCPM5-2B-CoreAI](https://huggingface.co/mlboydaisuke/MiniCPM5-2B-CoreAI) `ios-static/` @ `39db5ff9480e5d80e423889e3bacb7f9e9b9e40f` | | |
| | Qwen3.5 2B | [Qwen/Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B) | [mlboydaisuke/qwen3.5-2B-CoreAI](https://huggingface.co/mlboydaisuke/qwen3.5-2B-CoreAI) `gpu-pipelined-b2/qwen3_5_2b_decode_int8hu_block32_sym` @ `14e77014db5ae2f3de94825165f5ae58bededd7d` | | |
| | LFM2.5 1.2B | [LiquidAI/LFM2.5-1.2B-Instruct](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct) | [mlboydaisuke/LFM2.5-1.2B-CoreAI](https://huggingface.co/mlboydaisuke/LFM2.5-1.2B-CoreAI) `gpu-pipelined-b2/lfm2_5_1_2b_instruct_decode_int8hu_block32_sym` @ `3e3241cbcf368a663768dcc4e5785c4f0a02bae4` | | |
| ## Build | |
| Compiled on GitHub Actions (Xcode 27, Metal Toolchain) by | |
| [`compile-models.yml`](https://github.com/array-ai/fieldnotes/blob/main/.github/workflows/compile-models.yml): | |
| ``` | |
| xcrun coreai-build compile <model>.aimodel \ | |
| --platform iOS --min-deployment-version 27.0 --architecture <chip> --output <dir> | |
| ``` | |
| The MiniCPM5 1B bundles leave the compute unit to Core AI. The Qwen3.5, LFM2.5 and | |
| MiniCPM5 2B h18p bundles are compiled for the Neural Engine. Some on-device | |
| specialisation still happens at first load, but not the full compile. | |
| ## Loading | |
| ```swift | |
| import CoreAI | |
| import CoreAILanguageModels | |
| let chip = AIModel.deviceArchitectureName // e.g. "h17p" | |
| let bundle = modelsDirectory.appending(path: "qwen3.5-2b/ios-\(chip)") | |
| let model = try await CoreAILanguageModel(resourcesAt: bundle) | |
| ``` | |
| Fieldnote downloads only the matching folder, from a pinned revision of this repo, | |
| and checks every file against its SHA-256 before use. | |
| ## Licences | |
| This repo holds models under two licences. Each model's folder carries its own | |
| `LICENSE`: | |
| - **MiniCPM5 1B and 2B** (OpenBMB) and **Qwen3.5 2B** (Qwen team, Alibaba Cloud): | |
| [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0). The 1B's licence | |
| is the `LICENSE` at the repo root; the others are in `minicpm5-2b/` and `qwen3.5-2b/`. | |
| - **LFM2.5 1.2B Instruct** (Liquid AI): LFM Open License v1.0, in `lfm2.5-1.2b/LICENSE`. | |
| It allows commercial use only by organisations with under US$10 million in annual | |
| revenue; read it before using these bundles. | |
| Core AI exports by mlboydaisuke; ahead-of-time compiled builds by publicarray. The | |
| files here are modified from the originals only by being compiled for a specific chip. | |