Geekbench ML Score

480
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 02:32 PM
Views 1

System Information

System Information
Operating System iOS 16.1.2
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

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 380
40.7 IPS
 
Image Classification (F16)
100% 375
40.2 IPS
 
Image Classification (I8)
81% 285
30.5 IPS
 
Image Segmentation (F32)
100% 637
3.93 IPS
 
Image Segmentation (F16)
100% 628
3.88 IPS
 
Image Segmentation (I8)
89% 831
5.13 IPS
 
Pose Estimation (F32)
100% 209
0.85 IPS
 
Pose Estimation (F16)
100% 186
0.75 IPS
 
Pose Estimation (I8)
80% 191
0.77 IPS
 
Object Detection (F32)
100% 531
18.6 IPS
 
Object Detection (F16)
100% 534
18.7 IPS
 
Object Detection (I8)
52% 507
17.8 IPS
 
Face Detection (F32)
100% 681
7.83 IPS
 
Face Detection (F16)
100% 637
7.32 IPS
 
Face Detection (I8)
75% 579
6.65 IPS
 
Text Classification (F32)
100% 649
256.7 IPS
 
Text Classification (F16)
100% 699
276.7 IPS
 
Machine Translation (F32)
100% 745
114.9 IPS
 
Machine Translation (F16)
100% 732
112.8 IPS
 

Compare

Set Baseline