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

Intel perf table: Stable Diffusion FP16 on Flex 170, Intel TF 2.13, 6.45 its/s

6.45 iterations/s

Fields

id
benchmarks/intel-perf-flex170-stablediff-fp16-b1
Metric
tps_aggregate
Value
6.45
Unit
iterations/s
Model
Stable Diffusion (text prompts)
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 1. Weights FP16.
Measured by
vendor
notes
Iterations/sec for image generation, batch 1. Vision/generation rows - first measured coverage for this part.

Notes

Iterations/sec for image generation, batch 1. Vision/generation rows - first measured coverage for this part.

Cross-references