Edge AI & Robotics – Page 5

MobileNet v3 vs EfficientNet-Lite: Pi 4 Latency Benchmarks

2026년 02월 14일

Compare MobileNet v3 vs EfficientNet-Lite on Raspberry Pi 4 with real latency benchmarks. The winner might surprise you—see the full results.

2026년 02월 11일

Cut mobile inference from 200ms to 8ms by switching to ONNX Runtime. Benchmarks, CoreML quirks, and when TFLite still wins.

2026년 02월 07일

INT8 quantization pushed YOLOv8 from 45 to 180 FPS on Jetson Orin Nano. PTQ beat QAT with 10 lines of calibration code. Here's the recipe.

2026년 02월 06일

Deploy keyword spotting and anomaly detection on ESP32 for under $10. Quantization guide cuts model size 75% with minimal accuracy loss.

2026년 02월 04일

Whisper's encoder-decoder uses 1.5GB VRAM for Large model. Break down the architecture and memory bottlenecks before mobile deployment.

2026년 01월 18일

Real-time Whisper drains 1% battery/min. VAD + adaptive inference + thermal throttling bring it down to 0.2%. Benchmarks on iPhone 13 Pro.

2026년 01월 17일

ONNX Runtime + CoreML beats native Core ML for Whisper on iOS by 40%. Conversion script, memory pool tricks, and A15/A16 benchmark numbers.

2026년 01월 15일

Quantizing Whisper for mobile: post-training quantization failed, QAT crashed, but ONNX Runtime reduced model size 75% without accuracy loss.