Suggestions appear as you type. Use the up and down arrows to choose one and Enter to open it.

This page's audience our own tag's counts — open to see them
–Visits
–Page views
–Clicks to vendors
–Time on page
–Reading now
Clicks to vendors, by tool
  • –
Top countries
  • –
Devices
  • –

– · visits, page views and clicks counted by our own tag, which counts more than our checked analytics; every figure rounded down · how we count

StreamBench review

Free#55 of 72 in PC Benchmark Software

A focused command-line benchmark for memory bandwidth and local AI inference.

4.2/10Editor score
Visit StreamBench
StreamBench4.2 Visit StreamBench

Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026

StreamBench is a command-line PC benchmarking tool for measuring CPU and GPU memory bandwidth alongside local AI inference performance. It suits solo users and small teams that need focused testing across Windows, macOS, or Linux, especially when comparing memory workloads or evaluating AI models on CPU, GPU, and NPU hardware. Its CPU tests use the Copy, Scale, Add, and Triad kernels from the STREAM memory-bandwidth methodology, while GPU testing uses OpenCL.

The strongest distinction is its local AI testing coverage. StreamBench can measure model load time, response latency, and tokens per second across CPU, GPU, and NPU devices. Its integrations with Microsoft AI Foundry Local, LM Studio, and Ollama connect the benchmark to local AI tools, giving users a way to compare inference behavior across supported hardware. Range testing across multiple array sizes adds context to memory-bandwidth results, while automatic hardware and core detection reduces manual configuration.

For repeatable workflows, StreamBench saves results as JSON or CSV and supports custom test profiles and command-line automation. Pre-built binaries and launcher scripts are available for Windows and macOS, while the project also provides source-build instructions for Windows, macOS, and Linux. The open-source, self-hosted model fits users who want inspectable tooling and local execution rather than a commercial benchmarking service. Choose it for memory bandwidth and local AI inference analysis; choose a broader PC suite when you need a wider range of conventional benchmark categories.

StreamBench pros and cons

  • Where it wins
    • Tests CPU, GPU, and NPU AI inference workloads
    • Exports results in JSON or CSV formats
    • Supports Windows, macOS, and Linux
  • Where it doesn't
    • Its benchmark scope is narrower than general PC suites
    • Linux users need to build from source
    • The command-line workflow may not suit GUI-focused users

StreamBench fact sheet, pricing and score →

Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.

Last updated · How we research and update