Geekbench ML Score

460
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date July 16 2022 10:06 PM
Views 2

System Information

System Information
Operating System iOS 15.5
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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 375
40.2 IPS
 
Image Classification (F16)
100% 362
38.7 IPS
 
Image Classification (I8)
81% 283
30.4 IPS
 
Image Segmentation (F32)
100% 607
3.75 IPS
 
Image Segmentation (F16)
100% 602
3.72 IPS
 
Image Segmentation (I8)
89% 817
5.05 IPS
 
Pose Estimation (F32)
100% 200
0.81 IPS
 
Pose Estimation (F16)
100% 174
0.70 IPS
 
Pose Estimation (I8)
80% 193
0.78 IPS
 
Object Detection (F32)
100% 441
15.5 IPS
 
Object Detection (F16)
100% 529
18.6 IPS
 
Object Detection (I8)
52% 489
17.2 IPS
 
Face Detection (F32)
100% 663
7.61 IPS
 
Face Detection (F16)
100% 638
7.33 IPS
 
Face Detection (I8)
75% 564
6.47 IPS
 
Text Classification (F32)
100% 573
226.8 IPS
 
Text Classification (F16)
100% 648
256.3 IPS
 
Machine Translation (F32)
100% 717
110.5 IPS
 
Machine Translation (F16)
100% 729
112.4 IPS
 

Compare

Set Baseline Geekbench 6 now available