Skip to content

MLPerf Mobile App v5.0.1

Choose a tag to compare

View all tags
@anhappdev anhappdev released this 12 Sep 16:25
· 18 commits to master since this release
v5.0.1
7754341
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Description

MLPerf Mobile Inference Benchmark is an open-source benchmark suite for measuring how fast mobile devices (e.g. phones, laptops) can run AI tasks. The benchmark is supported by the MLPerf Mobile App which currently supports Android and iOS. Please see the MLPerf Mobile Inference benchmark paper for a detailed description of the benchmarks along with the motivation and guiding principles behind the benchmark suite.

Release Notes

This release includes important updates across device compatibility, backend improvements, app configuration, and UI fixes.

✨ Features & Improvements

• Added support for Mediatek mt6991 backend.
• Enhanced compatibility details for MLPerf app devices.
• Improved registration flow and introduced a simple resource flow.
• Made quick mode the default run mode.
• Increased cooldown slider max value to 30 minutes.
• Updated about, licensing, and privacy information.
• iOS app renamed to MLPerf Mobile and updated for Xcode 16.2.
• Increased Android targetSdkVersion to 35.
• Added support for models with different quantization.
• Resource UI and task screen usability improvements (scrollable task descriptions, overflow fixes, smoother iOS overscroll).
• Download button added for missing resources.

🛠️ CI/CD & Testing

• CI updated to use full commit SHA in GitHub Actions.
• Integrated Samsung Galaxy Tab S10 Plus for MTK tests and Galaxy S25 Ultra (Android 15.0) for QTI tests.
• Updated expected accuracy for QTI backend.
• CI improvements: BrowserStack log downloads, quick mode testing, larger datasets for integration tests.
• Fixes for BrowserStack failures on Qualcomm devices.
• Native debug symbols uploaded for improved debugging.

🐞 Fixes

• Fixed broken app drawer.
• Fixed iOS overscroll shaking issue on resource screen.
• Fixed task title overflow and improved scroll handling.

Full Changelog: v5.0...v5.0.1

Supported OSs

The MLPerf Mobile app supports Android 11 (API level 30) and above, as well as iOS 13.1 or later.

Supported SOCs

Mediatek

  • Dimensity 9000 series (9000/9000+/9200/9200+/9300/9300+/9400)
  • Dimensity 8000 series (8000/8020/8050/8100/8200/8300)

Qualcomm

  • Snapdragon 8 Elite
  • Snapdragon 8 Gen 3
  • Snapdragon 8s Gen 3
  • Snapdragon 8 Gen 2
  • Snapdragon 7 Gen 3
  • Snapdragon 7s Gen 3
  • Snapdragon 4 Gen 2
  • Default fallback for all other Snapdragon mobile platforms

Samsung

  • Exynos 2400
  • Exynos 2300
  • Exynos 2200
  • Exynos 2100

Google Pixel

  • Pixel 10/9/8/7/6 and Pixel 10/9/8/7/6 Pro (Tensor G5/G4/G3/G2/G1 SoC)

The MLPerf Mobile App will also run on a host of other devices via our default path, which uses TensorFlow Lite on Android devices.

Installation instructions

  1. Allow installation of unknown apps in Settings > Apps > Special Access.
  2. Download the MLPerf Mobile APK.
  3. Find the APK in 'Downloads' or file browser.
  4. Tap the APK file. Approve installation when prompted.
  5. Confirm 'Install'.
  6. Once installed, tap 'Open' to launch MLPerf Mobile.
# SHA256
377dcbb8b0411a6497060d92700652a964a7b636caa44786a5dd5eb5e0a8173f  2025-09-09_mlperfbench-qsmgt-571.apk
Assets 3
Loading