laya-coreml
Apache 2.0 Core ML port of Laya that runs typed decisions on the Apple Neural Engine, at about 5 ms per question on an M3 Max.
0 members list laya-coreml, unchanged over the last 12 weeks, data as of 11 November 2026
Members who list laya-coreml in their Stack, by week.
Members who list laya-coreml
Be the first to add laya-coreml
Nobody on Stackness runs laya-coreml yet. Add it to your stack and you're the first member running it.
About laya-coreml
laya-coreml is a Core ML implementation of Laya that enables typed decision models to run locally on Apple devices using the Neural Engine. The tool is designed for developers building on-device AI applications that require fast inference, supporting decision-making workflows without relying on cloud services. Laya handles structured reasoning tasks, and this port optimizes them for Apple Silicon hardware. The developer mizorewww created this implementation to provide validated ports of the decision framework with reproducible performance characteristics across Apple machines.
The project is written in Python and licensed under Apache 2.0, making it open source and freely available for use and modification. It targets developers who need efficient local inference on Apple platforms, particularly those working with modernBERT models or other language-based decision systems. The implementation focuses on practical performance metrics and energy efficiency for on-device deployment scenarios.
Checked 9 November 2026.
Nobody on Stackness runs laya-coreml yet.
Sign up and add itPosts about laya-coreml
- Strands Decider 2B: what it is and where it sits in an agent harness
Strands Decider 2B is AWS's free 1.9B decision model, out 1 October 2026: about 115 ms per question on an RTX 3090, consulted before each tool call.
- How do you run System One decision models locally? Ollaya, laya-mlx and the runtime slot
To run a System One model locally, pick a runtime too: Ollaya serves ten open model families, laya-mlx runs Laya on Apple silicon, and llama.cpp needs a shim.
- What people built on Jev in its first week, and which stack slot each project fills
Jev's first week brought a trusted monitor, computer-use agents, self-hosted clones, a benchmark and a joke chatbot: the slot each fills and which numbers hold.