Geekbench ML Score

529
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 22 2024 03:02 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% 560
60.0 IPS
 
Image Classification (F16)
100% 578
61.9 IPS
 
Image Classification (I8)
81% 146
15.6 IPS
 
Image Segmentation (F32)
100% 1543
9.53 IPS
 
Image Segmentation (F16)
100% 2551
15.8 IPS
 
Image Segmentation (I8)
89% 267
1.65 IPS
 
Pose Estimation (F32)
100% 645
2.61 IPS
 
Pose Estimation (F16)
100% 1212
4.90 IPS
 
Pose Estimation (I8)
80% 57
0.23 IPS
 
Object Detection (F32)
100% 823
28.9 IPS
 
Object Detection (F16)
100% 857
30.1 IPS
 
Object Detection (I8)
52% 209
7.32 IPS
 
Face Detection (F32)
100% 1481
17.0 IPS
 
Face Detection (F16)
97% 2667
30.6 IPS
 
Face Detection (I8)
75% 192
2.21 IPS
 
Text Classification (F32)
100% 395
156.1 IPS
 
Text Classification (F16)
98% 526
207.9 IPS
 
Machine Translation (F32)
100% 331
51.0 IPS
 
Machine Translation (F16)
100% 329
50.7 IPS
 

Compare

Set Baseline Geekbench 6 now available