MLPerf Client

Summary

MLPerf Client is ranked #6 of 66 in PC benchmark software on Samsung Mobile US Press. It runs on iOS, Linux, macOS, Windows.

Compared on PC benchmark software

Free plan

Yesmlcommons.org

Workload areas

LLM inference; image generation; agentic AImlcommons.org

Operating systems

Windows 11; macOS Tahoe 26; iPadOS 26; Ubuntu Linux 24.04mlcommons.org

Result export formats

CSVmlcommons.org

Custom test profiles

Yesmlcommons.org

CLI or automation

Yesmlcommons.org

Facts

Purpose

MLPerf Client benchmarks LLM, image generation, and agentic AI performance on personal computers, including laptops, desktops, and workstations.mlcommons.org · 8 Oct 2026

LLM workloads

Base LLM tasks include creative writing, content generation, structured text, code analysis, and intermediate summarization.mlcommons.org · 8 Oct 2026

Image generation

The image generation test uses the experimental Flux 2 Klein 4B model and measures images per minute at 1024×1024 resolution.mlcommons.org · 8 Oct 2026

Agentic AI

Agentic tests include Software Engineering and Data Analyst tasks and measure end-to-end duration, including LLM inference and tool execution.mlcommons.org · 8 Oct 2026

Supported systems

The stated operating system requirements are Windows 11 x86-64 or Arm, macOS Tahoe 26, iPadOS 26, and Ubuntu Linux 24.04.mlcommons.org · 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.mlcommons.org · 8 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.mlcommons.org · 8 Oct 2026

Result validity

Only scores produced with configurations marked “Configuration tested by MLCommons” are considered valid MLPerf Client scores.mlcommons.org · 8 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.mlcommons.org · 8 Oct 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.mlcommons.org · 8 Oct 2026

Support

The working group accepts support questions, problem reports, and feature requests through a form and says it will review and respond as needed.mlcommons.org · 8 Oct 2026

Maker

MLCommons describes itself as an AI engineering consortium built on open collaboration among industry and academia.mlcommons.org · 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.mlcommons.org · 9 Oct 2026

Hardware requirements

Minimum hardware requirements list selected AMD, Intel, NVIDIA, Qualcomm, and Apple systems, with memory and VRAM requirements varying by platform.mlcommons.org · 9 Oct 2026

Storage requirement

The benchmark requires 200GB of free drive space and recommends 400GB to run all models.mlcommons.org · 9 Oct 2026

Scoring limits

Only base components can contribute to an official MLCommons-tested score; extended and experimental results are marked separately.mlcommons.org · 9 Oct 2026

Quality checks

The working group applies MMLU and IFEval accuracy requirements to qualify accelerated execution paths and models for release.mlcommons.org · 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.mlcommons.org · 9 Oct 2026

Maker history

MLCommons' history page lists its launch as December 3, 2020.mlcommons.org · 9 Oct 2026

Where it ranks on Samsung Mobile US Press

• Best PC Benchmark Software in 2026#6 of 66

Sources

• mlcommons.org/benchmarks/client/· checked 8 Oct 2026
• mlcommons.org/about-us/· checked 8 Oct 2026