Stackness
Log inSign up
Sign up
Core ML

Core ML

Apple's framework for running machine learning models on device across the CPU, GPU and Neural Engine.

0 members list Core ML, unchanged over the last 12 weeks, data as of 7 November 2026

AI ToolsLanguages & FrameworksWebsite
Usage on Stackness
0membersunchanged over the last 12 weeks

Members who list Core ML in their Stack, by week.

Members who list Core ML

010Aug 22Nov 7
Source: Stackness stacks, week of Nov 7, 2026

Be the first to add Core ML

Nobody on Stackness runs Core ML yet. Add it to your stack and you're the first member running it.

Sign up and add it

Nobody on Stackness runs Core ML yet.

Sign up and add it

Moves that use Core ML

MoveAI Tools

Run small decision models locally via Apple CoreML for millisecond latency

Compile small, task-specific decision models, not full general-purpose LLMs, to run on Apple Silicon's Neural Engine using CoreML, achieving single-digit millisecond inference for narrow, real-time decisions like browser automation clicks or log routing choices. Developers port open-weight decision models to CoreML and benchmark decisions per second on M-series Macs, favoring on-device hardware acceleration over calling a hosted API for latency-sensitive, high-frequency decisions. What it is Instead of routing every small, structured decision to a hosted LLM API, you compile a narrow, task-specific decision model to Apple's Core ML format and run it on the Neural Engine of an M-series Mac. The model does not generate text token by token; it produces typed answers (a probability, a label, a field value) from a single forward pass. This is the approach behind open-weight ports like Laya-CoreML, which replace calls to a hosted decision API with local inference. How to do it Pick a genuinely narrow decision, such as classifying urgency in a support message, choosing the next browser click, or routing a log line, rather than open-ended generation. Port or download an existing open-weight decision model built for this pattern, such as the Laya models distributed for Core ML on Hugging Face. Compile the model with Core ML tooling so it targets the Neural Engine (ANE) rather than CPU or GPU execution. Wire the compiled model into your pipeline so it answers one typed question per call, keeping any general text-to-structure translation (like turning a goal into field values) as a separate, less frequent step handled by a text model if needed. Benchmark using decisions per second and P50/P95 latency on your target Mac, and compare against a compiled MLX or hosted-API baseline before committing. When it helps This fits latency-sensitive, high-frequency decisions where a network round trip to a hosted model is the bottleneck. Reported figures include a median around 33 ms on an M1 Max for one port, and single-question decisions around 4.9 to 5.3 ms P50/P95 on an M3 Max with ANE FP16, with one active game-loop benchmark sustaining close to 50 decisions per second. A palette-quantized variant pushed latency slightly lower while also improving energy per decision. Pitfalls This path is Apple Silicon only, requiring an M-series Mac and a current macOS and Python version, so it does not help teams targeting Windows or Linux deployment. It also only replaces the narrow decision step: workflows that still need a general text model to turn a goal into structured inputs still make one such call per task, so the local model is not a full LLM replacement.

Stackness00
See all moves that use Core ML

Posts about Core ML