mizorewww/laya-mlx
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
Open-weight typed decisions, running natively on Apple Silicon. 中文 · Usage reference · Benchmarks · Hugging Face weights · Changelog Laya answers constrained questions (pick an option, score against a rubric, judge true or false) with calibrated probabilities from one bidirectional forward pass. It generates no tokens and returns no JSON to parse. This package runs the original Laya weights in MLX, without PyTorch, Transformers or a cloud API. 13.4 ms median for a short English decision, 7.4 ms with the multilingual checkpoint (M3 Max, FP16). Requires Apple Silicon, macOS 14+ and Python 3.11+. Describing each option, as above, works much better than bare labels. The first load downloads the checkpoint; later inference is fully local. States can be text, JSON-like dicts or conversation lists. Each answer carries calibrated probabilities and confidence fields; confidence does not guarantee accuracy on a new task. laya.load accepts either column. Context counts instructions, options…
Read the full README ↗ · Preview checked 2026-11-01T10:52:13.414Z
Inside the original README — Document outline
- Laya-MLX
- Quick start
- Question types
- Checkpoints
- What else it does
- Performance
- Snake demo
- Relationship to upstream
- Contributing
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
Repository facts
- Owner
- mizorewww
- Primary language
- Python
- Stars
- 6,974
- Forks
- 569
- Open issues + pull requests
- 0
- License
- Apache-2.0
- Archived
- No
- Default branch
- main
- Created
- 2026-09-19T13:50:26.000Z
- Last push
- 2026-10-10T01:40:05.000Z
Topics and intended use
Owner-supplied topics: apple-silicon, decision-model, inference, laya, local-ai, machine-learning, mlx, modernbert, system-one, typed-decisions
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-19T12:11:29.441Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer