Geekbench ML Score

1801
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date March 11 2022 12:06 AM
Views 48

System Information

System Information
Operating System iOS 15.4
Model iPhone14,6
Model IDiPhone14,6
Motherboard D49AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.79 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1699
182.0 IPS
 
Image Classification (F16)
100% 2460
263.6 IPS
 
Image Classification (I8)
81% 668
71.6 IPS
 
Image Segmentation (F32)
100% 5242
32.4 IPS
 
Image Segmentation (F16)
100% 7292
45.0 IPS
 
Image Segmentation (I8)
89% 1149
7.10 IPS
 
Pose Estimation (F32)
100% 1758
7.11 IPS
 
Pose Estimation (F16)
100% 4171
16.9 IPS
 
Pose Estimation (I8)
80% 218
0.88 IPS
 
Object Detection (F32)
100% 1586
55.7 IPS
 
Object Detection (F16)
100% 3157
110.8 IPS
 
Object Detection (I8)
52% 907
31.8 IPS
 
Face Detection (F32)
100% 4787
55.0 IPS
 
Face Detection (F16)
97% 5886
67.6 IPS
 
Face Detection (I8)
75% 851
9.77 IPS
 
Text Classification (F32)
100% 868
343.4 IPS
 
Text Classification (F16)
100% 1010
399.3 IPS
 
Machine Translation (F32)
100% 1956
301.4 IPS
 
Machine Translation (F16)
100% 1956
301.5 IPS
 

Compare

Set Baseline Geekbench 6 now available