GPU Stress Test

Category

Dev Tools

How to Use

1. Choose a stress profile and rendering scale
2. Click "Start Test" to begin continuous GPU load
3. Monitor FPS, P95 frame time, dropped frames, and stability score in real time
4. Enable Auto Ramp to gradually increase load when performance remains stable

Examples

• Balanced 5-minute stress run

  Input: Profile: Balanced | Scale: 1.2x | Auto Ramp: On

  Output: Avg FPS 58.4 | P95 23.9ms | Stability 86

• Extreme quick probe

  Input: Profile: Extreme | Scale: 1.6x | Auto Ramp: Off

  Output: Avg FPS 33.2 | Dropped 142 frames | Lower scale for long runs

FAQ

Why does this differ from native FurMark scores?

Browser tests run inside a sandbox with different scheduler and safety behavior. Use it mainly for relative comparisons on the same machine and environment.

How should I read the stability score?

The score combines frame-time variance and drop rate. Higher values indicate smoother sustained output under the current load level.

What should I watch during testing?

Keep background load low and power stable. If the browser stutters heavily or system warnings appear, stop and lower profile/scale.

Related tools

• UUID Generator

  Batch generate UUID v4 with one-click copy

• Timestamp Converter

  Convert between timestamps and date/time formats

• Regex Tester

  Test and debug regular expressions in real time

• Hash Generator

  Compute MD5, SHA1, SHA256 hash values

• GPU Benchmark

  Run a fixed WebGPU scene for 60 seconds and sum per-second FPS as the final score

• WebNN NPU Compute Measurement

  Estimate effective NPU compute available to the browser by running a WebNN NPU-only matrix multiplication workload

• Local AI Model Runner

  Upload an ONNX model or enter a model download URL, then run browser-local inference with WebNN NPU/GPU first

• QR Code Generator

  Generate custom QR codes with advanced features like colors, logo, and batch generation