Geekbench ML Score

905
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 13 2023 09:22 AM
Views 4

System Information

System Information
Operating System iOS 17.0
Model iPhone14,6
Model IDiPhone14,6
Motherboard D49AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.80 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 754
80.8 IPS
 
Image Classification (F16)
100% 717
76.9 IPS
 
Image Classification (I8)
81% 456
48.9 IPS
 
Image Segmentation (F32)
100% 1046
6.46 IPS
 
Image Segmentation (F16)
100% 988
6.10 IPS
 
Image Segmentation (I8)
89% 1430
8.84 IPS
 
Pose Estimation (F32)
100% 390
1.58 IPS
 
Pose Estimation (F16)
100% 388
1.57 IPS
 
Pose Estimation (I8)
80% 466
1.88 IPS
 
Object Detection (F32)
100% 1034
36.3 IPS
 
Object Detection (F16)
100% 1029
36.1 IPS
 
Object Detection (I8)
52% 756
26.5 IPS
 
Face Detection (F32)
100% 1276
14.7 IPS
 
Face Detection (F16)
100% 1100
12.6 IPS
 
Face Detection (I8)
75% 1065
12.2 IPS
 
Text Classification (F32)
100% 1055
417.3 IPS
 
Text Classification (F16)
100% 1084
428.8 IPS
 
Machine Translation (F32)
100% 2065
318.3 IPS
 
Machine Translation (F16)
100% 2058
317.2 IPS
 

Compare

Set Baseline Geekbench 6 now available