Geekbench ML Score

2312
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 23 2021 03:22 AM
Views 2

System Information

System Information
Operating System iOS 15.1
Model iPhone14,2
Model IDiPhone14,2
Motherboard D63AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.24 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.56 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2856
306.0 IPS
 
Image Classification (F16)
100% 4450
476.8 IPS
 
Image Classification (I8)
81% 695
74.4 IPS
 
Image Segmentation (F32)
100% 5978
36.9 IPS
 
Image Segmentation (F16)
100% 8294
51.2 IPS
 
Image Segmentation (I8)
89% 1221
7.54 IPS
 
Pose Estimation (F32)
100% 1918
7.76 IPS
 
Pose Estimation (F16)
100% 4908
19.9 IPS
 
Pose Estimation (I8)
80% 231
0.94 IPS
 
Object Detection (F32)
100% 3208
112.6 IPS
 
Object Detection (F16)
100% 3311
116.2 IPS
 
Object Detection (I8)
52% 969
34.0 IPS
 
Face Detection (F32)
100% 5215
59.9 IPS
 
Face Detection (F16)
97% 9287
106.7 IPS
 
Face Detection (I8)
75% 917
10.5 IPS
 
Text Classification (F32)
100% 1913
756.7 IPS
 
Text Classification (F16)
100% 2142
847.1 IPS
 
Machine Translation (F32)
100% 1941
299.2 IPS
 
Machine Translation (F16)
100% 1954
301.2 IPS
 

Compare

Set Baseline Geekbench 6 now available