Anvil, an iPhone app built by a local-model developer, runs Gemma 4 E2B chat via LiteRT LM and an SDXL image model converted to Core ML on the Neural Engine at 1024x1024, with both models never loaded…
Ortus AI released RightWayUp, an Apache-2.0 licensed 360° image rotation model that predicts how far an image is rotated (0–359°) with a confidence score and abstains when it cannot determine which wa…
A developer built a Simplified Chinese iPhone app, 他爱我吗, that runs a Core ML conversion of the laya-multilingual model entirely on-device to score candidate answers to relationship questions such as a…
Laya released laya-coreml, an open-weight Core ML model that runs typed decision inference locally on Apple Silicon's Neural Engine, sustaining 49.1–50.0 decisions/s across three uncapped 600-step Sna…
A developer has demonstrated that Apple's built-in Sound Analysis classifier (SNClassifySoundRequest, .version1) lacks a cat_hiss class, offering only cat_meow and cat_purr while including snake_hiss.…
Skydio posted a Senior Autonomy Engineer - Computer Vision role in San Mateo, California, with an annual base salary range of $170,000 to $277,500. The listing, filed under Core ML roles, sits 6% belo…
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)…
Glance, a new macOS app, brings FaceID-like face unlock to Macs using on-device Apple Vision and Core ML frameworks, converting faces into 512-dimensional embeddings stored locally with AES-GCM encryp…
Apple's upcoming M6 and M5 Ultra chips will redefine local AI by delivering massive increases in unified memory bandwidth and dedicated transformer silicon, according to a report. The new architecture…
Local-first workspace software can eliminate the need for cloud indexing by leveraging on-device AI and search capabilities, according to a guide from Neutron Tech. Modern hardware such as Apple Silic…
VoxHearth, an open-source macOS menu bar app for private dictation, records audio in memory, transcribes with a bundled Core ML model, and inserts text into the focused app, with no account, telemetry…
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…
A developer with 18 years of iOS experience built AIAnalyzer, a Swift CLI tool that detects architectural code smells and offers AI-generated fix suggestions through a hybrid system that decides wheth…
DictaFlow's Local Offline Mode enables dictation on Windows, Apple silicon Macs, and iPhones without an internet connection using on-device models like NVIDIA's Parakeet TDT 0.6B v3, while competitor …
A developer built a Swift 6 actor topology that routes on-device inference requests between MLX's GPU compute and Core ML's ANE scheduler on Apple Silicon, achieving sub-50ms first-token latency on qu…
Swipe Cleaner, an iOS app built on the OpenNomos ecosystem, processes all photo cleaning tasks on-device using Apple's Core ML and Vision frameworks, ensuring no user data leaves the device. The app e…
A developer presents a hybrid edge AI architecture for mobile applications that performs intent classification locally using a lightweight machine learning model, reserving cloud-based LLMs for ambigu…
A developer built an AI-powered photo management app called Swipe Cleaner using SwiftUI and Core ML after struggling with storage issues on their iPhone. The app uses on-device processing with Vision …
Swipe Cleaner, part of the Opennomos ecosystem, processes all photo cleaning entirely on-device using Core ML, Vision, and Metal, with no network requests for photo processing. The app's architecture …
Apple's decade-long investment in custom silicon, including neural processing and unified memory, has positioned its devices as the preferred platform for AI developers, with Macs dominating frontier …