Geekbench ML Score

126
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 20 2024 03:16 AM
Views 3

System Information

System Information
Operating System iOS 15.6
Model iPhone X
Model IDiPhone10,6
Motherboard D221AP
CPU Information
Name Apple A11 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.39 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 2.76 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 95
10.2 IPS
 
Image Classification (F16)
100% 100
10.7 IPS
 
Image Classification (I8)
81% 89
9.55 IPS
 
Image Segmentation (F32)
100% 175
1.08 IPS
 
Image Segmentation (F16)
100% 188
1.16 IPS
 
Image Segmentation (I8)
89% 308
1.90 IPS
 
Pose Estimation (F32)
100% 60
0.24 IPS
 
Pose Estimation (F16)
100% 56
0.23 IPS
 
Pose Estimation (I8)
80% 72
0.29 IPS
 
Object Detection (F32)
100% 182
6.38 IPS
 
Object Detection (F16)
100% 182
6.37 IPS
 
Object Detection (I8)
52% 157
5.52 IPS
 
Face Detection (F32)
100% 173
1.99 IPS
 
Face Detection (F16)
100% 154
1.77 IPS
 
Face Detection (I8)
75% 151
1.73 IPS
 
Text Classification (F32)
100% 109
43.3 IPS
 
Text Classification (F16)
100% 110
43.5 IPS
 
Machine Translation (F32)
100% 124
19.2 IPS
 
Machine Translation (F16)
100% 131
20.2 IPS
 

Compare

Set Baseline Geekbench 6 now available