Geekbench ML Score

690
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

User hrdc0r3
Upload Date January 17 2025 10:12 AM
Views 4

System Information

System Information
Operating System iOS 15.8.3
Model iPhone 7
Model IDiPhone9,3
Motherboard D101AP
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% 568
60.8 IPS
 
Image Classification (F16)
100% 596
63.9 IPS
 
Image Classification (I8)
81% 315
33.8 IPS
 
Image Segmentation (F32)
100% 1513
9.35 IPS
 
Image Segmentation (F16)
100% 2526
15.6 IPS
 
Image Segmentation (I8)
89% 551
3.40 IPS
 
Pose Estimation (F32)
100% 636
2.57 IPS
 
Pose Estimation (F16)
100% 1199
4.85 IPS
 
Pose Estimation (I8)
80% 118
0.48 IPS
 
Object Detection (F32)
100% 915
32.1 IPS
 
Object Detection (F16)
100% 1063
37.3 IPS
 
Object Detection (I8)
52% 398
14.0 IPS
 
Face Detection (F32)
100% 1457
16.7 IPS
 
Face Detection (F16)
97% 2648
30.4 IPS
 
Face Detection (I8)
75% 360
4.13 IPS
 
Text Classification (F32)
100% 407
160.8 IPS
 
Text Classification (F16)
98% 551
217.9 IPS
 
Machine Translation (F32)
100% 560
86.2 IPS
 
Machine Translation (F16)
100% 646
99.6 IPS
 

Compare

Set Baseline Geekbench 6 now available