# mizorewww/laya-coreml

> Local port of the Laya model to Apple Core ML and Neural Engine: returns typed decisions (choice, score, yes/no) without token generation, with speed and energy benchmarks.

- Magnitude: 0.9 out of 10 — Quiet
- Stars: 1,609 total · +2 stars measured 2026-10-28, 00:12–18:24 UTC, ≈ 3 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2026-09-19 · Last push: 2026-10-20
- GitHub: https://github.com/mizorewww/laya-coreml · Homepage: https://github.com/mizorewww/laya-coreml#readme · Page: https://gitnova.dev/en/r/mizorewww/laya-coreml

## Useful for

- Run the local Snake demo agent on Apple Silicon without PyTorch or MLX
- Get typed decisions (choice/score/yes-no) from short text offline
- Compare Core ML ANE energy and latency against compiled MLX FP16

## Why it’s here

- Star-counter measurements on 2026-10-28 (UTC), 00:12–18:24: 1607 → 1609 stars (+2). This is the change over that interval.
- Estimated end-of-day forecast: about +3 stars, using observed gains and the previous day.
- The repository is 39 days old and already has 1,609 stars.
- Recent forks include notable developers: @christopherkarani (223 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 136
- Issues and pull requests: 7
- Watchers: 8
- Average over the last week: 2 per day
- Usual pace: 10 per day
- Latest release: v0.5.1 (2026-10-20)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-06 … 2026-11-04: 5, 9, 4, 3, 3, 0, 7, 4, 5, 1, 1, 0, 2, 2, 1, 5, 3, 2, 2, 2, 2, 2, 1, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

10-15 1.1, 10-16 0.7, 10-17 0.5, 10-18 0.4, 10-19 0.6, 10-20 0.8, 10-21 1.0, 10-22 1.4, 10-23 1.2, 10-24 1.1, 10-25 1.0, 10-26 1.0, 10-27 0.8, 10-28 0.9

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-28 18:26 UTC, updated every 30 minutes.