Tag: Edge AI
-
Raspberry Pi 5 vs Jetson Nano: MobileNet Inference 38ms Gap
Pi 5 hits 38ms INT8 inference vs Jetson's 12ms โ but costs $90 less. Real TFLite/ONNX benchmarks reveal when each board wins.
-
Whisper Tiny vs faster-whisper: 3x Speed, 12% WER Gap
faster-whisper cuts Jetson Nano latency 68% but WER jumps to 20%. Real benchmarks, memory spikes, and the thermal throttling nobody mentions.
-
INT8 vs INT4 Quantization: 2x Latency Drop on ARM Cortex-M
INT4 quantization cuts Cortex-M inference latency in half โ but costs 18KB flash, breaks on residual nets, and drops accuracy 4-6% on edge cases.
-
TFLite vs ONNX Runtime: Pi Zero Latency at 32ms vs 89ms
Benchmark TFLite vs ONNX Runtime on Raspberry Pi Zero: which framework delivers faster inference? Latency comparison reveals clear winner.
-
ONNX Runtime vs TFLite Android: 3x Speed Benchmark
Compare ONNX Runtime vs TensorFlow Lite on Android with real benchmarks. Discover which framework delivers 3x faster mobile inference performance.
-
MobileNet v3 vs EfficientNet-Lite: Pi 4 Latency Benchmarks
Compare MobileNet v3 vs EfficientNet-Lite on Raspberry Pi 4 with real latency benchmarks. The winner might surprise youโsee the full results.
-
ONNX Runtime Mobile: 8ms Inference on iPhone 13
Cut mobile inference from 200ms to 8ms by switching to ONNX Runtime. Benchmarks, CoreML quirks, and when TFLite still wins.
-
Edge AI Object Detection: YOLO Mobile Optimization Guide
YOLOv5n at 320px beats over-engineered quantization for mobile MVPs. Preprocessing tricks and NMS optimization that actually ship.