choose-apple-model-runtime
/choose-apple-model-runtime
Porównuje i wybiera runtime modeli na Apple: Core AI, Core ML, MLX, MLX Swift, MLX LM, delegaty ExecuTorch lub Foundation Models, wraz z przekazaniem do implementacji.
- Autor
- gaelic-ghost ↗
- Repozytorium
- socket ↗
- Licencja
- Apache-2.0
- Ostatnia zmiana repozytorium
- 26.08.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 3
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 26.08.2026, bez odwołań do wycofanych modeli i API.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
Co robi i kiedy
Porównuje i wybiera runtime modeli na Apple: Core AI, Core ML, MLX, MLX Swift, MLX LM, delegaty ExecuTorch lub Foundation Models, wraz z przekazaniem do implementacji.
Oryginalny opis (EN)
Compare and select Core AI, Core ML, MLX, MLX Swift, MLX LM, ExecuTorch Apple delegates, or Foundation Models. Use when an Apple model workflow needs a runtime choice and implementation handoff.
Jak działa
- Route By Artifact And Constraint
- Decision Workflow
- Important Distinctions
- References
Podgląd SKILL.md
--- name: choose-apple-model-runtime description: Compare and select Core AI, Core ML, MLX, MLX Swift, MLX LM, ExecuTorch Apple delegates, or Foundation Models. Use when an Apple model workflow needs a runtime choice and implementation handoff. --- # Choose Apple Model Runtime ## Route By Artifact And Constraint | Need | Start with | | --- | --- | | Host a downloaded model locally for an API client, agent framework, or dev tool | LM Studio local server; choose native `/api/v1` model-management APIs or OpenAI-compatible `/v1` inference APIs deliberately | | Author `.aimodel` packages with editable Python primitives and Swift runtime utilities | Choose Core AI, then hand off to the `coreai-models` `working-with-coreai` and `model-authoring` skills | | Lower `torch.export.ExportedProgram` into Core AI IR | `coreai-torch` | | Quantize, palettize, or prune Core AI models | Choose Core AI, then hand off to Apple's `model-compression-exploration` skill and `coreai-optimization` | | Convert and deploy established Core ML model packages | `coremltools` plus Core ML | | Train or run tensor programs natively on Apple silicon | MLX | | Integrate MLX models in Swift | MLX Swift | | Fine-tune or serve supported language models with MLX | MLX LM | | Use one ExecuTorch `.pte` pipeline with Apple acceleration | Compare the ExecuTorch Core ML backend and experimental MLX delegate | | Use Apple's system on-device language model without shipping weights | Foundation Models framework; use Python Apple FM SDK for supported Python access | ## Decision Workflow 1. Decide whether the need is a local inference server for a client or an app-packaged runtime/artifact. Use LM Studio for the former; identify the source artifact for the latter. 2. Identify the deployment API: Python research, Swift app, ExecuTorch C++/mobile, or Foundation Models. 3. Consult the dated maturity and availability matrix in `references/apple-model-tooling.md`, then confirm OS, Xcode, SDK, device, architecture, operator, dynamic-shape, state/cache, and precision requirements against the current official source. 4. Select the shortest supported conversion path. Do not round-trip through formats merely because converters exist. 5. Prototype one representative subgraph and one stateful generation step before converting the full model. 6. Evaluate numerical/behavioral parity on the exact packaged artifact. 7. Benchmark on the target device with `benchmark-model-runtime`. 8. Return the selected runtime, maturity class, source revision/date checked, unmet availability gates, and implementation owner. Hand Core AI authoring/compression to Apple's named skills and app-facing Swift/Xcode work to `apple-dev-skills`. ## Important Distinctions - Core AI and Core ML are related Apple deployment surfaces but are not interchangeable artifact formats or APIs. - MLX is a general Apple-silicon array framework; MLX LM and MLX Swift are distinct higher-level/use-language surfaces. - ExecuTorch's MLX delegate is marked experimental and under active development upstream. Treat support as revision-specific and compare it separately with the Core ML backend. - Foundation Models uses Apple's system model and availability contract; it is not a route for packaging arbitrary user-supplied weights. - LM Studio is a local model server and control plane, not a Core AI, Core ML, MLX, or Foundation Models artifact/runtime. Its endpoint compatibility does not prove model tool use or structured-output behavior. - Apple research repositories vary from reusable frameworks to benchmark or paper-reproduction code. Classify the repository before recommending it as infrastructure. ## References Read `references/apple-model-tooling.md` for the official source map and verification checklist.
Pliki w paczce (3)
- SKILL.md 4 KB
- agents/openai.yaml 1 KB
- references/apple-model-tooling.md 6 KB
Wersje
W bazie nie ma innych skilli o nazwie choose-apple-model-runtime.
Identyczna treść występuje jeszcze w 1 innych folderach na GitHubie. Tu pokazujemy jedną, najlepiej ocenioną kopię.
Migawka bazy z 13.11.2026 · wersja paczki dace3d3be8e4 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 90benchmark-model-runtime
Porównuje środowiska uruchomieniowe modeli pod kątem opóźnień, przepustowości, pamięci, energii, czasu ładowania, rozmiaru i stabilności: Core AI, Core ML, MLX, ExecuTorch, PyTorch. - 100minicpm5-deploy-mlx
Uruchamia MiniCPM5-1B lub MiniCPM5-2B natywnie na Apple Silicon w frameworku MLX, z użyciem mlx_lm, w tym mlx_lm.convert i mlx_lm.generate. - 95apple-on-device-ai
Integruje AI na urządzeniu: Foundation Models, Core ML (konwersja, kwantyzacja, Neural Engine), MLX Swift i llama.cpp z modelami GGUF na Apple Silicon. - 100apple-on-device-ai
Obsługuje generatywną AI na urządzeniu w iOS 26 i nowszych: Foundation Models, sesje, guided generation, tool calling i guardrails oraz wybór między Core ML, MLX Swift a llama.cpp. - 100local-model-orchestrator
Skanuje, objaśnia, dobiera, instaluje i wywołuje lokalne modele AI w Ollama, cache Hugging Face, MLX Whisper, whisper.cpp i LM Studio, z naciskiem na modele zoptymalizowane pod Apple Silicon. - 100minicpm5-deploy-lmstudio
Uruchamia MiniCPM5-1B lub MiniCPM5-2B w LM Studio przez środowisko GGUF albo szybsze MLX na Apple Silicon, z lokalnym serwerem zgodnym z OpenAI i interfejsem czatu bez kodowania.