MLPerf Client
The facts below are what the maker publishes about MLPerf Client, checked and dated. Our editors have not written about it yet.
The facts
Each one read from MLPerf Client's own pages, with the date it was checked.
What it does
- Agentic AI
- Agentic tests cover Software Engineering and Data Analyst tasks and measure end-to-end duration, including LLM inference and tool execution.checked 9 Oct 2026
- CLI or automation
- Yeschecked 23 Sep 2026
- Custom test profiles
- Yeschecked 23 Sep 2026
- Download and source
- The benchmark is downloadable from its GitHub release page, and its public GitHub repository contains source code that users may inspect or modify.checked 8 Oct 2026
- Downloads
- The benchmark is downloadable from GitHub, its iPad version is available in Apple's App Store, and its public GitHub repository contains source code.checked 9 Oct 2026
- Experimental components
- The Linux CLI version, power-efficiency tools, Flux 2 Klein 4B image generation, and some agentic workloads are identified as experimental.checked 8 Oct 2026
- Hardware limits
- The benchmark requires 200GB of free drive space and recommends 400GB to run all models; minimum hardware and memory requirements vary by platform.checked 8 Oct 2026
- Hardware requirements
- Minimum hardware requirements list selected AMD, Intel, NVIDIA, Qualcomm, and Apple systems, with memory and VRAM requirements varying by platform.checked 9 Oct 2026
- Image generation
- The image generation test uses the experimental Flux 2 Klein 4B model and reports images per minute at 1024×1024 resolution.checked 9 Oct 2026
- Internet use
- An internet connection is needed for the first run with an acceleration path; downloaded files are stored locally for later runs.checked 8 Oct 2026
- LLM workloads
- Its LLM tasks include creative writing, content generation, structured text, code analysis, and summarization, using models including Llama 3.1 8B Instruct and Phi 4 Mini Instruct.checked 9 Oct 2026
- Network use
- An internet connection is needed for the first run with an acceleration path to download files; later runs use locally stored files.checked 9 Oct 2026
- Operating systems
- Windows 11; macOS Tahoe 26; iPadOS 26; Ubuntu Linux 24.04checked 23 Sep 2026
- Purpose
- MLPerf Client benchmarks LLM, generative image, and agentic AI performance on personal computers, including laptops, desktops, and workstations.checked 9 Oct 2026
- Quality checks
- The working group applies MMLU and IFEval accuracy requirements to qualify accelerated execution paths and models for release.checked 9 Oct 2026
- Result export formats
- CSVchecked 23 Sep 2026
- Result validity
- Only scores produced with configurations marked “Configuration tested by MLCommons” are considered valid MLPerf Client scores.checked 8 Oct 2026
- Scoring limits
- Only base components can contribute to an official MLCommons-tested score; extended and experimental results are marked separately.checked 9 Oct 2026
- Storage requirement
- The benchmark requires 200GB of free drive space and recommends 400GB to run all models.checked 9 Oct 2026
- Support
- Users can submit questions, feature requests, or problems through the support form for working-group review and response as needed.checked 9 Oct 2026
- Supported systems
- The stated operating system requirements are Windows 11, macOS Tahoe 26, iPadOS 26, or Ubuntu Linux 24.04; Linux is described as CLI-only and experimental.checked 9 Oct 2026
Money
- Free plan
- Yeschecked 23 Sep 2026
The company
- Maker
- MLCommons describes itself as an open AI engineering consortium that develops benchmarks through collaboration between industry and academia.checked 9 Oct 2026
- Maker history
- MLCommons' history page lists its launch as December 3, 2020.checked 9 Oct 2026
Alternatives to MLPerf Client
- 1
Geekbench
Free planAndroidiOSLinuxmacOS8.6$99 one-time - 2
CrossMark
Free planAndroidiOSLinuxmacOS8.0Free plan - 3
ZBrush
Free planiOSAPImacOSWindows7.9Free plan - 4
SiSoftware Sandra
Free planAndroidWindows7.8$74.99 one-time - 5
SPECapc for Siemens NX 2024
Free planWindows7.7Free plan - 6
UNIGINE Valley Benchmark
Free planLinuxmacOSWindows7.7$14.95 one-time