AIAC-BR-2026-01: Comparative INT8 vs FP16 Inference Latencies for YOLOv8 on NVIDIA Jetson Hardware

Vikas M., Chetan L., Deepak G.

AIAC Benchmark Reports · 2026-03-25

Abstract

Empirical benchmarking of frame throughput, memory bandwidth saturation, and thermal profiling across TensorRT compiled vision graphs on Jetson embedded boards. Reports exact latency curves across batch sizes 1 to 8 under realistic ambient thermal conditions.

Cite this Work

@techreport{aiac_bm_2026_01,
  title = {AIAC-BR-2026-01: Comparative INT8 vs FP16 Inference Latencies for YOLOv8 on NVIDIA Jetson Hardware},
  author = {Vikas M., Chetan L., Deepak G.},
  institution = {AI & Analytics Club Research Division},
  year = {2026},
  url = {https://aiac.siddharthgupta.com.np/outputs/bm-2026-01}
}

License & Open Access

Distribution: This work is released under CC BY 4.0. You are free to share and adapt the material provided appropriate attribution is credited to AIAC and original student authors.