Test My GPU
Run real Compute, Memory, and AI Matrix workloads on this PC's GPU directly in the browser, with no installation.
All tests run inside this browser.
Real GPU Benchmark
Each workload is auto-calibrated to avoid very short measurements, then measured repeatedly using the median.
YOLO Training Setup
YOLO Training Setup
YOLO11 Small · 640 · Detection
9.4M params · 21.5B FLOPs @ 640
VRAM and speed estimates change with the selected YOLO model and image size. Dataset Images and Epochs are used to estimate training time.
Browsers may hide the exact GPU model, so the user selects it manually. The WebGPU benchmark still runs on the actual GPU independently of this selection.
Compute
Repeated FMA shader throughput
Memory
Storage-buffer read + write throughput proxy
AI Matrix
1024×1024 tiled matrix multiplication
Production use requires HTTPS. localhost can be used for local WebGPU development.
WebGPU Benchmark
Starting the test runs real Compute / Memory / Matrix workloads on this PC's GPU.
How v2 measures
To prevent command-submit overhead from dominating fast GPUs, each workload automatically increases its repeat count. GPU timestamps are preferred when supported; otherwise v2 uses a sufficiently long calibrated wall-clock workload.
Next step
The next step is to calibrate this v2 score against measured RTX 5060 CUDA/PyTorch/YOLO results, enabling WebGPU score → YOLO recommended batch and training-speed estimates.
Important
WebGPU is not the same API or workload as PyTorch CUDA training. At this stage, WebGPU results alone are not used to claim an exact YOLO batch size or training time.
How to use
- Start the GPU test in your browser.
- Choose a workload and test settings.
- Review performance metrics and the reference YOLO result when it finishes.