Geekbench ML Score

716
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

User 46fy45
Upload Date August 29 2024 04:08 AM
Views 3

System Information

System Information
Operating System iOS 15.8.2
Model iPhone 7 Plus
Model IDiPhone9,2
Motherboard D11AP
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 2.93 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 568
60.8 IPS
 
Image Classification (F16)
100% 587
62.9 IPS
 
Image Classification (I8)
81% 317
34.0 IPS
 
Image Segmentation (F32)
100% 1536
9.49 IPS
 
Image Segmentation (F16)
100% 2564
15.8 IPS
 
Image Segmentation (I8)
89% 584
3.61 IPS
 
Pose Estimation (F32)
100% 640
2.59 IPS
 
Pose Estimation (F16)
100% 1211
4.90 IPS
 
Pose Estimation (I8)
80% 124
0.50 IPS
 
Object Detection (F32)
100% 942
33.1 IPS
 
Object Detection (F16)
100% 1128
39.6 IPS
 
Object Detection (I8)
52% 455
16.0 IPS
 
Face Detection (F32)
100% 1477
17.0 IPS
 
Face Detection (F16)
97% 2696
31.0 IPS
 
Face Detection (I8)
75% 405
4.65 IPS
 
Text Classification (F32)
100% 410
162.1 IPS
 
Text Classification (F16)
98% 546
216.0 IPS
 
Machine Translation (F32)
100% 667
102.7 IPS
 
Machine Translation (F16)
100% 660
101.8 IPS
 

Compare

Set Baseline Geekbench 6 now available