# PulzeMark — benchmark AI, LLM, CPU > benchmark AI, LLM, CPU (iPhone/iPad app by FLORIN CRISTIAN NEMES.) - Source: https://appshunter.io/ios/app/pulzemark/id6759485137 (this page in markdown: same URL + `.md`) - Developer: [FLORIN CRISTIAN NEMES](https://appshunter.io/developer/1865508889) - Category: Utilities, Developer Tools - Price: Free - Age rating: 4+ - Requires: iOS 18.6 · 27 MB - Languages: American English - Released: 2026-07-09 - Data updated: 2026-08-26 - User reviews in markdown: https://appshunter.io/ios/app/pulzemark/id6759485137/reviews.md ## What is PulzeMark? PulzeMark measures how fast your iPhone and iPad really are: CPU, storage, and on-device AI, all in one app. Every result is scored and compared against a live, anonymous, crowdsourced leaderboard, so you can see exactly where your device stands. ON-DEVICE AI BENCHMARK Download a free, open-source language model and run it entirely on your device. PulzeMark measures how many tokens per second your iPhone or iPad generates, plus prompt throughput and time to first token. No cloud, no account. Two engines, each with its own leaderboard: Apple-native MLX for peak performance, and GGUF (llama.cpp) with cross-platform leaderboards, where identical models put every device on the same board. Compare your device against others running the same model at the same output length. CPU AND REAL-WORLD TESTS Single-core and multi-core CPU, plus real workloads: integer and floating point math, cryptography, compression, photo processing, and UI layout. Scores share one unified scale across platforms, so equal numbers mean equal performance. You get a clear score and a live timeline of CPU usage and thermal state during the run. STORAGE SPEED Sequential and random read and write, with configurable file size, block size, and passes. See your real disk throughput in MB/s. COMPARE EVERYTHING Results are crowdsourced anonymously. Compare your device per category and per AI model, browse every device ever benchmarked, and explore the full cross-platform leaderboard on the web. PRIVATE BY DESIGN No sign-in, no tracking, no personal data. Submissions are anonymous: just the device model, scores, and raw metrics. FEATURES - CPU single-core and multi-core benchmarks - Real-world tests: photo processing and UI layout - Storage read and write, sequential and random - On-device LLM benchmark in tokens per second - Two AI engines: Apple-native MLX and cross-platform GGUF (llama.cpp) - Manage downloaded models and their storage from Settings - Live CPU and thermal monitoring during runs - Crowdsourced, anonymous leaderboards - Per-model AI comparison across devices - Shareable result cards - Works on iPhone and iPad Benchmark your device, then see how it stacks up against the world. ## Version history (last 3 releases) ### 1.1.0 — 2026-08-04 NEW: cross-platform GGUF engine (llama.cpp). Download and benchmark GGUF models alongside Apple-native MLX, each on its own leaderboard, with GGUF results comparable cross-platforms. NEW: Manage Downloaded Models in Settings: see how much space each model uses, delete one, or clear them all. NEW: The floating monitor card is now draggable, and tapping it jumps straight to the running benchmark. NEW: Get a heads-up when a newer version of PulzeMark is available. IMPROVED: A clear "Loading model into memory" phase shows before generation starts on large models. IMPROVED: Scoring recalibrated for consistency across devices and platforms. Multi-Core scores may read lower than before; leaderboard comparisons stay fair because everyone is measured the same way. IMPROVED: Benchmarks now stop safely if the app moves to the background, protecting score accuracy. FIXED: More accurate prompt speed measurement for GGUF models. FIXED: iPhone XS, XS Max, XR and 2018-2020 iPads now show their proper names in Device Info. ### 1.0.5 — 2026-07-15 AI tab redesign: your latest tokens/sec now sits right next to the neural pulse, and while a benchmark runs the screen stays focused on the live answer and system monitor. New 1024-token endurance length, plus an "Epic story" prompt built to fill long runs. The default length is now 256 tokens. The 64-token option was retired: runs that short measured startup noise, not real speed. Battery section in Device Info: charge level, power source, and Low Power Mode at a glance. Low Power Mode protection: the app now warns you before benchmarking with Low Power Mode on, and those runs stay on your device so throttled scores never skew the community leaderboards. iPhone 17e is now recognized by name. Small fixes and polish. ### 1.0.4 — 2026-07-09 No release notes. ## More apps by FLORIN CRISTIAN NEMES - [My Grocery Plan](https://appshunter.io/ios/app/my-grocery-plan/id6757313533) All apps by FLORIN CRISTIAN NEMES: https://appshunter.io/developer/1865508889 --- *Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-08-26.*