inference/research
verifiedmedium · 0.75updated 2026-10-15

Intel perf table: ResNet-50 v1.5 INT8 on Flex 170, OpenVINO, 9499 img/s (b256)

9499.0 inferences/s

Fields

id
benchmarks/intel-perf-flex170-resnet50-int8-b256
Metric
tps_aggregate
Value
9,499
Unit
inferences/s
Model
ResNet-50 v1.5 (ImageNet2012)
Methodology
VENDOR-MEASURED (Intel AI performance table, measured 2023-10-24). 1x Intel Data Center GPU Flex 170 on Xeon Platinum 8360Y 2S-36C-72T host, 128GB DDR4-3200, Ubuntu 22.04. OpenVINO 2023.2, INT8 precision. Unit = images/sec (inferences/sec), NOT tokens - CV inference rows for the uncovered accel record. Batch size 256.
Measured by
vendor
notes
Vendor table, batch-256 throughput row. Vision/generation rows - first measured coverage for this part.

Notes

Vendor table, batch-256 throughput row. Vision/generation rows - first measured coverage for this part.

Cross-references