Geekbench ML Score

511
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 09:58 PM
Views 1

System Information

System Information
Operating System iOS 16.1.2
Model iPhone 8
Model IDiPhone10,1
Motherboard D20AP
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 1.93 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 382
40.9 IPS
 
Image Classification (F16)
100% 380
40.8 IPS
 
Image Classification (I8)
81% 286
30.6 IPS
 
Image Segmentation (F32)
100% 658
4.07 IPS
 
Image Segmentation (F16)
100% 655
4.05 IPS
 
Image Segmentation (I8)
89% 862
5.32 IPS
 
Pose Estimation (F32)
100% 224
0.91 IPS
 
Pose Estimation (F16)
100% 218
0.88 IPS
 
Pose Estimation (I8)
80% 237
0.96 IPS
 
Object Detection (F32)
100% 585
20.5 IPS
 
Object Detection (F16)
100% 611
21.5 IPS
 
Object Detection (I8)
52% 521
18.3 IPS
 
Face Detection (F32)
100% 719
8.26 IPS
 
Face Detection (F16)
100% 720
8.28 IPS
 
Face Detection (I8)
75% 580
6.66 IPS
 
Text Classification (F32)
100% 715
282.7 IPS
 
Text Classification (F16)
100% 729
288.2 IPS
 
Machine Translation (F32)
100% 744
114.6 IPS
 
Machine Translation (F16)
100% 752
115.8 IPS
 

Compare

Set Baseline