Geekbench ML Score

1825
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 21 2021 06:58 AM
Views 1

System Information

System Information
Operating System iOS 15.0.2
Model iPhone14,4
Model IDiPhone14,4
Motherboard D16AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.61 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1644
176.2 IPS
 
Image Classification (F16)
100% 1497
160.4 IPS
 
Image Classification (I8)
81% 700
75.0 IPS
 
Image Segmentation (F32)
100% 5296
32.7 IPS
 
Image Segmentation (F16)
100% 7323
45.2 IPS
 
Image Segmentation (I8)
89% 1243
7.68 IPS
 
Pose Estimation (F32)
100% 1772
7.17 IPS
 
Pose Estimation (F16)
100% 4212
17.0 IPS
 
Pose Estimation (I8)
80% 232
0.94 IPS
 
Object Detection (F32)
100% 2085
73.2 IPS
 
Object Detection (F16)
100% 3052
107.1 IPS
 
Object Detection (I8)
52% 949
33.3 IPS
 
Face Detection (F32)
100% 4868
55.9 IPS
 
Face Detection (F16)
97% 5835
67.0 IPS
 
Face Detection (I8)
75% 920
10.6 IPS
 
Text Classification (F32)
100% 969
383.1 IPS
 
Text Classification (F16)
100% 1086
429.3 IPS
 
Machine Translation (F32)
100% 1977
304.7 IPS
 
Machine Translation (F16)
100% 1968
303.4 IPS
 

Compare

Set Baseline Geekbench 6 now available