> Canonical page: https://posttrainllm.com/learn/artifacts/mac-runtime-boundary-map

Buildable artifact · stage 8

# Mac runtime boundary map

A comparison of owned MLX weights, Core ML deployment, Apple Foundation Models, and browser runtimes grounded in measured capability limits.

**Readiness**
 guided replay

**Kind**
 architecture decision record

**Workload**
 read-only evidence synthesis

**Stage**
 Cross runtime boundaries

## Artifact contract

A comparison of owned MLX weights, Core ML deployment, Apple Foundation Models, and browser runtimes grounded in measured capability limits.

This architecture decision record is classified as guided replay. Workload guidance: read-only evidence synthesis.

## Build

Map one use case across capability, context, RAM, energy, ownership, and distribution constraints.

## Modify

Add a new runtime only with a directly comparable evidence row.

## Tune

Tune routing and deployment policy; do not hide a capability gap behind serving changes.

## Prove

Use the same task gate plus latency, RAM, tok/s, energy, setup, and ownership constraints.

## Package

Record the chosen runtime, rejected alternatives, evidence, and reversal conditions.

## CLI surface

- Run: posttrainllm hf-load
- Run: posttrainllm ane-validate
- Run: posttrainllm coreml-serve

## How to read this dossier

This canonical page separates the retained repository decision from the material that informed it. A source may describe an external claim, historical measurement, local observation, or planned procedure; those evidence classes are not interchangeable. Follow the provenance links before reusing a number or method.

Status and disposition describe what PostTrainLLM retained when this record was indexed. They are not a live product promise, a newly run benchmark, or permission to restart historical work. Unknown or unmeasured fields remain unknown rather than being treated as zero.

To reuse the record, first name the exact claim you need and trace it to the linked source. Then check whether the original environment, model revision, data split, evaluator, hardware, and budget match the proposed use. If they do not, treat the record as a hypothesis or design reference and run the smallest fresh comparison that can falsify it. Preserve negative outcomes and regressions beside any improvement; a local win on one slice does not silently become a general capability claim.

## Source provenance

The normalized record comes from docs/learn/artifact-journey.json . The links below are the tracked evidence and explanatory sources preserved with the record.

- [scripts/fm_agent_bridge.swift ↗](https://github.com/PostTrainLLM/posttrainllm/blob/main/scripts/fm_agent_bridge.swift)
- [native-mac/Sources/TinyGPT/CoreMLServe.swift ↗](https://github.com/PostTrainLLM/posttrainllm/blob/main/native-mac/Sources/TinyGPT/CoreMLServe.swift)
- [Map one use case across capability, context, RAM, energy, ownership, and distribution constraints. ↗](https://posttrainllm.com/docs/learn/mac-mastery-map/)
- [Add a new runtime only with a directly comparable evidence row. ↗](https://posttrainllm.com/docs/learn/apple-on-device-foundation-models/)
- [Tune routing and deployment policy; do not hide a capability gap behind serving changes. ↗](https://posttrainllm.com/docs/learn/model-vs-agent/)
- [Record the chosen runtime, rejected alternatives, evidence, and reversal conditions. ↗](https://posttrainllm.com/docs/factory/reports/)

[Read the Markdown equivalent →](https://posttrainllm.com/learn/artifacts/mac-runtime-boundary-map.md)

Related evidence

- learning path [Cross runtime boundaries](https://posttrainllm.com/learn/paths/browser-and-mac-runtime)
- recipe [Parakeet WGSL browser ASR](https://posttrainllm.com/recipes/parakeet-browser-asr)

 Canonical record learning-artifact:mac-runtime-boundary-map