Bluetooth Browser vs Vector Search Bench

An iOS & macOS browser built with built-in Bluetooth Low Energy support, so you can control your devices directly from the web. Pair with any BLE-enabled device and connect from a web app. Send commands, trigger actions, and manage your setup over BLE without installing dedicated apps. Works great for ESPs, PyBricks (Lego Motors), OpenEarable, Storz & Bickel devices and any system that communicate over Bluetooth Low Energy using a web app. You can find our recommendations or browse to your own url at any time. The BLE browsing experience is free to use. If you like the app, you can support the developer with an optional tip. Terms of Use: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/ Privacy Policy: https://privacy.cammalleri.dev/

Vector Search Bench is a high-signal, no-nonsense benchmark suite for vector similarity search on iPhone. Measure how fast and stable your device can score embeddings using the CPU (Accelerate/vDSP) versus the Apple Neural Engine (Core ML)—with real metrics you can trust. What you can benchmark Exact Top-K vector search (dot-product similarity) CPU path: Accelerate / vDSP optimized scoring NPU path: Core ML Dense inference tuned for Neural Engine scheduling Query-by-query execution with repeatable timing Intricate performance metrics Latency distribution: median, p95 Throughput: QPS Recall@K vs CPU reference (sanity check) Memory footprint and dataset sizing knobs Built for real-world AI systems