SOURCE-LINKED INTELLIGENCE

Is INT8 Portable? A Cross-Platform Measurement Study of Quantized Inference on Embedded and Automotive Accelerators

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Eight-bit integer (INT8) post-training quantization is the default recipe for edge deployment, under a widely held assumption: INT8 makes inference faster at a small, predictable accuracy cost, and a model quantized once can be carried to any target. We test that assumption with a controlled measurement study across seven hardware classes -- ARM and x86 CPUs, a discrete GPU, an NVIDIA Jetson AGX Orin iGPU and its NVDLA cores, and two vendor NPUs (Qualcomm Hexagon HTP, DEEPX DX-M1) -- holding the ONNX artifact and the quantization scales fixed so the integer kernel or ISA is the only free varia

Read original source ↗ Open in workspace

recordType

paper

region

Global