Geekbench ML Score

660
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 08 2024 02:31 AM
Views 1

System Information

System Information
Operating System iOS 15.8.3
Model iPhone 7
Model IDiPhone9,1
Motherboard D10AP
CPU Information
Name Apple A10 Fusion
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.34 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.95 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 570
61.1 IPS
 
Image Classification (F16)
100% 583
62.4 IPS
 
Image Classification (I8)
81% 315
33.8 IPS
 
Image Segmentation (F32)
100% 1551
9.58 IPS
 
Image Segmentation (F16)
100% 2581
15.9 IPS
 
Image Segmentation (I8)
89% 582
3.60 IPS
 
Pose Estimation (F32)
100% 645
2.61 IPS
 
Pose Estimation (F16)
100% 1216
4.92 IPS
 
Pose Estimation (I8)
80% 113
0.46 IPS
 
Object Detection (F32)
100% 889
31.2 IPS
 
Object Detection (F16)
100% 1065
37.4 IPS
 
Object Detection (I8)
52% 319
11.2 IPS
 
Face Detection (F32)
100% 1485
17.1 IPS
 
Face Detection (F16)
97% 2701
31.0 IPS
 
Face Detection (I8)
75% 292
3.35 IPS
 
Text Classification (F32)
100% 399
157.7 IPS
 
Text Classification (F16)
98% 535
211.8 IPS
 
Machine Translation (F32)
100% 486
74.9 IPS
 
Machine Translation (F16)
100% 477
73.6 IPS
 

Compare

Set Baseline Geekbench 6 now available