HomeBenchmarks › NVIDIA L4 (24GB)
Benchmark Explorer · NVIDIA L4 (24GB)

NVIDIA L4 (24GB): 9 benchmark rows, 0% measured.

Method v1.0 · dataset 2026-09-07 · verified 2026-09-07 · last updated September 2026

0 of 9 rows are measured and published (class C); the rest are EdgeAIStack-derived (class D). 4 model families. Precisions: FP16 (8), INT8 (1). Runtimes: tensorrt (9). Tasks: detection (8), classification (1).

Family × precision: best value

The fastest matching row per family and precision (fps, or tokens/s for language models), with its evidence class. Click a cell for the full breakdown.

FamilyFP16INT8
EfficientDet920 fps D
ResNet4800 fps D
YOLO11862 fps D1150 fps D
YOLOv8816 fps D

Every model on NVIDIA L4 (24GB)

Query this hardware live.

Filter by model, precision or runtime and get the matching rows with a permanent link.

OPEN BENCHMARK EXPLORER →