A developer released a portable profiler that measures Apple Neural Engine KernelDMA prefetch behavior across M1, M3, M4, and M5 chips by timing the private _ANEClient evaluateWithModel call (eval_us)…
Slop or Not, an AI text and image detector for iPhone and Mac, runs entirely offline with no account required, using on-device AI models powered by the Apple Neural Engine to detect AI-generated conte…
A developer has reverse-engineered Apple's private APIs to train neural networks directly on the Apple Neural Engine (ANE), bypassing CoreML's inference-only restriction. The project, which uses the _…
Maple-Preview, a 20B parameter Mixture-of-Experts transformer quantized to ternary weights, achieves 120 tokens per second on an iPhone, according to a developer preview. The model, which runs on Appl…
Reflex launched Glass, an always-on screen recording app that uses secure, local inference on Apple's Neural Engine to provide visual context for AI agents. The app aims to enrich personal context by …
ANEForge, a new open-source Python package, compiles tensor graphs directly into programs for the Apple Neural Engine (ANE) and runs them without CoreML, enabling both inference and training on the ch…
A developer successfully ran Google's Gemma 4 E2B and E4B models on Apple's Neural Engine (ANE) using CoreML, achieving a memory footprint under 1 GB on an iPhone 17 Pro. The project overcame ANE's la…
Apple announced RAW 9, a major overhaul of its RAW image processing engine coming with iOS 27, using a CoreML model to improve detail and reduce noise, including for older photos. The update leverages…
Researchers reverse-engineered the Apple Neural Engine (ANE), documenting its architecture, programming interface, and performance across A11-A18 and M1-M5 chips. The study reveals a direct user-space…
A developer built an offline skin lesion segmenter for mobile devices by optimizing the Med-SAM model with CoreML and ONNX Runtime. The approach enables real-time, privacy-preserving segmentation on i…
Researchers at an undisclosed institution reverse-engineered Apple's Metal 4.1 tensor compute path on the M4 Max GPU, revealing that the fp8 matmul2d operation is emulated rather than hardware-acceler…