Geekbench ML Score

701
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 15 2024 06:39 PM
Views 3

System Information

System Information
Operating System iOS 15.8.3
Model iPhone 7 Plus
Model IDiPhone9,4
Motherboard D111AP
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% 566
60.7 IPS
 
Image Classification (F16)
100% 581
62.3 IPS
 
Image Classification (I8)
81% 318
34.1 IPS
 
Image Segmentation (F32)
100% 1536
9.49 IPS
 
Image Segmentation (F16)
100% 2548
15.7 IPS
 
Image Segmentation (I8)
89% 564
3.49 IPS
 
Pose Estimation (F32)
100% 639
2.58 IPS
 
Pose Estimation (F16)
100% 1212
4.90 IPS
 
Pose Estimation (I8)
80% 119
0.48 IPS
 
Object Detection (F32)
100% 940
33.0 IPS
 
Object Detection (F16)
100% 1208
42.4 IPS
 
Object Detection (I8)
52% 437
15.3 IPS
 
Face Detection (F32)
100% 1481
17.0 IPS
 
Face Detection (F16)
97% 2700
31.0 IPS
 
Face Detection (I8)
75% 372
4.27 IPS
 
Text Classification (F32)
100% 405
160.1 IPS
 
Text Classification (F16)
98% 544
215.3 IPS
 
Machine Translation (F32)
100% 600
92.4 IPS
 
Machine Translation (F16)
100% 573
88.3 IPS
 

Compare

Set Baseline Geekbench 6 now available