Geekbench ML Score

1080
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 07:00 PM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPhone 11
Model IDiPhone12,1
Motherboard N104AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.76 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1131
121.2 IPS
 
Image Classification (F16)
100% 1420
152.2 IPS
 
Image Classification (I8)
81% 283
30.3 IPS
 
Image Segmentation (F32)
100% 3223
19.9 IPS
 
Image Segmentation (F16)
100% 5325
32.9 IPS
 
Image Segmentation (I8)
89% 519
3.21 IPS
 
Pose Estimation (F32)
100% 1326
5.37 IPS
 
Pose Estimation (F16)
100% 3747
15.2 IPS
 
Pose Estimation (I8)
80% 98
0.40 IPS
 
Object Detection (F32)
100% 1390
48.8 IPS
 
Object Detection (F16)
99% 1648
57.8 IPS
 
Object Detection (I8)
52% 401
14.1 IPS
 
Face Detection (F32)
100% 3261
37.5 IPS
 
Face Detection (F16)
97% 4924
56.6 IPS
 
Face Detection (I8)
75% 394
4.53 IPS
 
Text Classification (F32)
100% 855
338.2 IPS
 
Text Classification (F16)
98% 1059
418.8 IPS
 
Machine Translation (F32)
100% 648
99.8 IPS
 
Machine Translation (F16)
100% 650
100.2 IPS
 

Compare

Set Baseline