📱 Edge AI Lab
Drag quantization bit-depth and pruning percentage and watch model size, inference latency and accuracy trade off against each other for on-device AI.
AI & Machine Learning2DModerate60 FPS
⚙ Under the hood
Drag quantization bit-depth and pruning percentage and watch model size, inference latency and accuracy trade off against each other for on-device AI.
edge-aiquantizationpruning
2D · HTML5 Canvas 2D · 60 FPS target · runs fully client-side, no install