--- license: apache-2.0 base_model: OpenMOSS-Team/MOSS-Transcribe-Diarize pipeline_tag: audio-text-to-text library_name: coreai language: - en - zh widget: - text: "Explain on-device AI in one sentence." - text: "Write a haiku about Apple Silicon." tags: - coreai - core-ai - coreai-fabric - aimodel - coreml - apple - apple-silicon - on-device - iphone - metal - audio-text-to-text - llm --- > **Canonical:** [`kevinqz/MOSS-Transcribe-Diarize-Decoder-CoreAI`](https://huggingface.co/kevinqz/MOSS-Transcribe-Diarize-Decoder-CoreAI) — source of truth. # MOSS-Transcribe-Diarize Qwen3 Decoder (fabric) **Apple Core AI chat model — runs fully on-device on Apple Silicon (iPhone / iPad / Mac, macOS/iOS 27+).** A quantized **stateful KV-cache chat** `.aimodel` — an Apple Core AI conversion of [OpenMOSS-Team/MOSS-Transcribe-Diarize](https://huggingface.co/OpenMOSS-Team/MOSS-Transcribe-Diarize), with an embedded tokenizer + chat template. Produced by [coreai-fabric](https://github.com/kevinqz/coreai-fabric/blob/main/recipes/moss-transcribe-diarize-decoder.yaml) and indexed by [coreai-catalog](https://github.com/kevinqz/coreai-catalog). ## Model facts | Field | Value | |---|---| | Parameters | 0.6B | | Architecture | transformer | | Capabilities | speech-to-text, text-generation | | Quantization / precision | none / float32 | | Context length | — | | On-disk size | 2.2 GB | | Asset kind | stateful KV-cache chat bundle; embedded tokenizer + chat template | | assetVersion | 2.0 | ## Use it Install via the catalog, then run it with Apple's Foundation Models runtime: ```bash pip install coreai-catalog && coreai-catalog install moss-transcribe-diarize-decoder ``` ```swift import CoreAILanguageModels import FoundationModels // modelURL = the installed macos/ bundle directory for this model let model = try await CoreAILanguageModel(resourcesAt: modelURL) let session = LanguageModelSession(model: model) let reply = try await session.respond(to: "Explain on-device AI in one sentence.") print(reply) ``` A complete, buildable example lives at [coreai-catalog/examples/llm-chat](https://github.com/kevinqz/coreai-catalog/tree/main/examples/llm-chat). ## Requirements - **Deployment: macOS 27.0+ / iOS 27.0+, Xcode 27+.** The asset serializes with `minimum_os v27`, so the on-device Swift runtime requires macOS/iOS 27+. - A Mac on **macOS 26 can convert and inspect** the asset but **cannot run** it on-device (the Swift runtime needs the 27 SDK). - Apple Silicon. ## Intended use & limitations - **Intended use:** general on-device chat / text generation. Inherits the base model's capabilities, languages, and biases. - **Limitations:** uncompressed (fp16) — full precision. See the Evaluation section for the measured greedy fidelity vs the fp16 reference. ## Evaluation (parity) - **Gate A (structure): passed** — the bundle's layout + metadata were validated on real hardware (Apple Silicon); the asset loads and generates. - **Gate B (numeric accuracy): passed.** Task-accuracy evaluation (e.g. tinyMMLU) is pending *upstream*: Apple's `coreai.llm.eval` is a stub in coreai-models 0.1.0 that cannot score a stateful KV-cache asset. Greedy fidelity vs fp32 can be measured on-device via the parity runner. fabric never fakes a parity number. - **Runtime throughput (tok/s):** to be published once measured on the on-device (macOS/iOS 27) Swift runtime. Not estimated — real numbers or none. ## Provenance | Field | Value | |---|---| | Base model | [OpenMOSS-Team/MOSS-Transcribe-Diarize](https://huggingface.co/OpenMOSS-Team/MOSS-Transcribe-Diarize) @ `d7231bbae2587a4af278735eb765b318c4f64edd` | | Converted by | `models/moss_transcribe/export_decoder.py` (version not reported) | | Recipe | [moss-transcribe-diarize-decoder](https://github.com/kevinqz/coreai-fabric/blob/main/recipes/moss-transcribe-diarize-decoder.yaml) (recipe_source: fabric) | | Precision / quantization | float32 / none | | Conversion date | 2026-07-10 | Machine-readable, in this repo: [`parity-report.json`](./parity-report.json) (gate results) · [`reproduce-manifest.json`](./reproduce-manifest.json) (exact tool + stack + pinned revision to reproduce this conversion) · [`LICENSE`](./LICENSE) (upstream terms). ## License and attribution Weights licensed **apache-2.0** — see the bundled `LICENSE`. This artifact is a **converted + quantized derivative** of the base model (the Apache-2.0 §4(b) change notice): weights were converted to Apple Core AI format and quantized to uncompressed (fp16). The conversion itself is community work. ## Links - **Base model:** [OpenMOSS-Team/MOSS-Transcribe-Diarize](https://huggingface.co/OpenMOSS-Team/MOSS-Transcribe-Diarize) - **Reproduce:** [recipe `moss-transcribe-diarize-decoder`](https://github.com/kevinqz/coreai-fabric/blob/main/recipes/moss-transcribe-diarize-decoder.yaml) · [runnable example](https://github.com/kevinqz/coreai-catalog/tree/main/examples/llm-chat) - **Index:** [coreai-catalog](https://github.com/kevinqz/coreai-catalog) — the neutral registry that ties upstream ↔ this asset ↔ mirror together - [HF Collection](https://huggingface.co/collections/kevinqz/coreai-apple-on-device-6a4879f21c7e1a87c99bcf5a) ## The on-device Core AI ecosystem This conversion is part of a broader open ecosystem for running models on Apple's on-device stack — useful references if you're building here: - [coreai-fabric](https://github.com/kevinqz/coreai-fabric) — the reproducible recipe → `.aimodel` pipeline that produced this asset. - [coreai-catalog](https://github.com/kevinqz/coreai-catalog) — the index of Core AI models across the community, with provenance and integration snippets. - [apple/coreai-models](https://github.com/apple/coreai-models) — Apple's official exporters and runtimes. - [CoreAI Model Zoo](https://github.com/john-rocky/coreai-model-zoo) and the wider [coreai-community](https://huggingface.co/coreai-community) — community conversions across many model families. ## Not affiliated with Apple Community conversion. Not produced, hosted, or endorsed by Apple. Apple and Core AI are trademarks of Apple Inc., used here only to describe the target runtime/format. This is an independent community conversion.