Wooden Clock vs MLX Benchmarks

There are literally hundreds of iPad "clock" apps ... so why make another? Wooden Clock is an homage to a time before clocks were digital and silent - before they became an expected set of numbers on every electronic device in a home or office - a time when things moved at a different, slower pace. The ticking of an old wooden clock is sadly something that many kids and adults have never had the opportunity to appreciate. This app humbly hopes to recreate some of the joy of old wooden clocks for those people and of course to serve as fun nostalgic app for those of us who remember them fondly. FEATURES: - Tells the time in old wooden clock style! - Rich custom clock graphics - One of the only iPad clock apps with a pendulum! - Includes soothing ticking and hourly chime sounds - Country skins use their national anthem for chime - Settings allow user to toggle ticking and chimes - Long or short chime option INCLUDED CLOCKS: - Wooden Clock (the original!) - Tibet Clock - France Clock - Russia - Germany - Sweden (newest!) - More to come as inspiration and time permits! NOTES: - Works best on iPad Air 1 or later but works on older iPads as well.

MLX Benchmark helps you understand how large language models perform on your hardware. Select a model and quantization, set context length and iterations, and run repeatable benchmarks that capture load time, tokenization time, time to first token, throughput, memory usage, and jitter. View detailed metrics grids, visualize comparisons in charts, and manage downloaded model repos directly in the app. Built for developers and AI enthusiasts who want clear, on-device performance insights without leaving their device. Features: - Model selection with quantization details - Configurable prompt, context length, and iterations - Metrics for load, tokenization, first-token latency, throughput, jitter, and memory - Charts to compare runs and devices - Downloaded model management (list, delete, refresh) - Optional Supabase upload for aggregating benchmark results