StreamBench
The facts below are what the maker publishes about StreamBench, checked and dated. Our editors have not written about it yet.
The facts
Each one read from StreamBench's own pages, with the date it was checked.
What it does
- AI backends
- The AI inference benchmark supports Microsoft Foundry Local, LM Studio, and Ollama.checked 11 Oct 2026
- AI integrations
- It supports Microsoft Foundry Local, LM Studio, and Ollama as AI backends.checked 11 Oct 2026
- AI measurements
- The AI benchmark reports model load time, first-run response time, and warm-run tokens per second.checked 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.checked 11 Oct 2026
- Automation
- Range testing can sweep array sizes and save consolidated CSV output.checked 11 Oct 2026
- CLI or automation
- Yeschecked 22 Sep 2026
- Custom test profiles
- Yeschecked 22 Sep 2026
- Downloads
- The project offers prebuilt binaries for Windows and macOS, with x64 and ARM64 variants.checked 11 Oct 2026
- GPU testing
- The GPU memory bandwidth backend uses OpenCL, which the project says is loaded dynamically without a GPU SDK dependency.checked 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.checked 11 Oct 2026
- Limits
- The project is focused on single-node benchmarking and does not include the MPI support listed for upstream STREAM.checked 11 Oct 2026
- Measured AI metrics
- It reports model load time, first-response time, and warm-run tokens per second.checked 11 Oct 2026
- Memory tests
- Its CPU and GPU benchmarks run the Copy, Scale, Add, and Triad STREAM kernels.checked 11 Oct 2026
- NPU limitation
- NPU benchmarking requires Foundry Local; the README says LM Studio and Ollama do not support NPU benchmarking.checked 11 Oct 2026
- Operating systems
- Windows; macOS; Linuxchecked 22 Sep 2026
- Privacy
- Saved results and CLI summaries may include hardware details and the hostname, and the project advises reviewing files before sharing them publicly.checked 11 Oct 2026
- Purpose
- StreamBench benchmarks memory bandwidth and AI inference across CPU, GPU, and NPU hardware.checked 11 Oct 2026
- Requirements
- AI benchmarking requires at least one supported AI backend, which the setup script can install.checked 11 Oct 2026
- Result export formats
- JSON; CSVchecked 22 Sep 2026
- Results
- The CLI displays benchmark results and can save them in JSON and CSV formats.checked 11 Oct 2026
Where it runs
- Device coverage
- Foundry Local supports CPU, GPU, and NPU benchmarking; LM Studio and Ollama do not support NPU benchmarking.checked 11 Oct 2026
- Linux support
- The README documents macOS and Linux launch scripts and says the project can be built from source on Linux.checked 11 Oct 2026
- macOS limitation
- Foundry Local on macOS currently supports GPU mode only, without CPU or NPU device targeting.checked 11 Oct 2026
- Platforms
- Prebuilt downloads are offered for Windows and macOS, while the project also documents Linux use and source builds.checked 11 Oct 2026
Alternatives to StreamBench
- 1
Geekbench
Free planAndroidiOSLinuxmacOS7.8$99 one-time - 2
Blender
Free planOpen sourceLinuxmacOSWindows7.5Free plan - 3
CrossMark
Free planAndroidiOSLinuxmacOS7.5Free plan - 4
Novabench
Free planLinuxmacOSWindows7.2From $36 a year - 5
Parkdale
Free planAndroidmacOSWindows7.2Free plan - 6
Basemark GPU
Free planAndroidiOSLinuxmacOS7.1Free plan