Geekbench ML Score

462
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 12 2024 12:08 AM
Views 2

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% 562
60.2 IPS
 
Image Classification (F16)
100% 575
61.6 IPS
 
Image Classification (I8)
81% 139
14.9 IPS
 
Image Segmentation (F32)
100% 1529
9.44 IPS
 
Image Segmentation (F16)
100% 2527
15.6 IPS
 
Image Segmentation (I8)
89% 222
1.37 IPS
 
Pose Estimation (F32)
100% 641
2.59 IPS
 
Pose Estimation (F16)
100% 1206
4.88 IPS
 
Pose Estimation (I8)
80% 45
0.18 IPS
 
Object Detection (F32)
100% 693
24.3 IPS
 
Object Detection (F16)
100% 726
25.5 IPS
 
Object Detection (I8)
52% 155
5.43 IPS
 
Face Detection (F32)
100% 1450
16.7 IPS
 
Face Detection (F16)
97% 2595
29.8 IPS
 
Face Detection (I8)
75% 138
1.58 IPS
 
Text Classification (F32)
100% 381
150.5 IPS
 
Text Classification (F16)
98% 511
202.1 IPS
 
Machine Translation (F32)
100% 203
31.2 IPS
 
Machine Translation (F16)
100% 202
31.1 IPS
 

Compare

Set Baseline Geekbench 6 now available