StreamBench

On the record

AI backends

The AI inference benchmark supports Microsoft Foundry Local, LM Studio, and Ollama.github.com · read 11 Oct 2026

AI integrations

It supports Microsoft Foundry Local, LM Studio, and Ollama as AI backends.github.com · read 11 Oct 2026

AI measurements

The AI benchmark reports model load time, first-run response time, and warm-run tokens per second.github.com · read 11 Oct 2026

Array size

The README recommends using arrays at least four times larger than the largest cache and notes that small sizes can be skewed by cache effects.github.com · read 11 Oct 2026

Automation

Range testing can sweep array sizes and save consolidated CSV output.github.com · read 11 Oct 2026

CLI or automation

Yesgithub.com · read 22 Sep 2026

Custom test profiles

Yesgithub.com · read 22 Sep 2026

Device coverage

Foundry Local supports CPU, GPU, and NPU benchmarking; LM Studio and Ollama do not support NPU benchmarking.github.com · read 11 Oct 2026

Downloads

The project offers prebuilt binaries for Windows and macOS, with x64 and ARM64 variants.github.com · read 11 Oct 2026

GPU testing

The GPU memory bandwidth backend uses OpenCL, which the project says is loaded dynamically without a GPU SDK dependency.github.com · read 11 Oct 2026

Intended users

The README describes it as aimed at users seeking a quick visual benchmark with prebuilt binaries, GPU coverage, and AI inference comparisons on modern hardware.github.com · read 11 Oct 2026

Limits

The project is focused on single-node benchmarking and does not include the MPI support listed for upstream STREAM.github.com · read 11 Oct 2026

Linux support

The README documents macOS and Linux launch scripts and says the project can be built from source on Linux.github.com · read 11 Oct 2026

macOS limitation

Foundry Local on macOS currently supports GPU mode only, without CPU or NPU device targeting.github.com · read 11 Oct 2026

Measured AI metrics

It reports model load time, first-response time, and warm-run tokens per second.github.com · read 11 Oct 2026

Memory tests

Its CPU and GPU benchmarks run the Copy, Scale, Add, and Triad STREAM kernels.github.com · read 11 Oct 2026

NPU limitation

NPU benchmarking requires Foundry Local; the README says LM Studio and Ollama do not support NPU benchmarking.github.com · read 11 Oct 2026

Operating systems

Windows; macOS; Linuxgithub.com · read 22 Sep 2026

Alternatives to StreamBench

Every alternative, ranked