Geekbench ML Score

424
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 15 2021 09:55 AM
Views 1

System Information

System Information
Operating System iOS 14.8
Model iPhone 8
Model IDiPhone10,4
Motherboard D201AP
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% 367
39.4 IPS
 
Image Classification (F16)
100% 304
32.6 IPS
 
Image Classification (I8)
81% 428
45.8 IPS
 
Image Segmentation (F32)
100% 472
2.92 IPS
 
Image Segmentation (F16)
100% 542
3.35 IPS
 
Image Segmentation (I8)
89% 796
4.92 IPS
 
Pose Estimation (F32)
100% 187
0.76 IPS
 
Pose Estimation (F16)
100% 151
0.61 IPS
 
Pose Estimation (I8)
80% 167
0.67 IPS
 
Object Detection (F32)
100% 436
15.3 IPS
 
Object Detection (F16)
100% 446
15.6 IPS
 
Object Detection (I8)
52% 493
17.3 IPS
 
Face Detection (F32)
100% 567
6.51 IPS
 
Face Detection (F16)
100% 552
6.34 IPS
 
Face Detection (I8)
75% 579
6.65 IPS
 
Text Classification (F32)
100% 435
172.0 IPS
 
Text Classification (F16)
100% 580
229.5 IPS
 
Machine Translation (F32)
100% 622
95.9 IPS
 
Machine Translation (F16)
100% 675
104.0 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download