Geekbench ML Score

1402
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 09 2024 06:36 PM
Views 1

System Information

System Information
Operating System iOS 17.6.1
Model iPhone16,2
Model IDiPhone16,2
Motherboard D84AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.77 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.44 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1071
114.7 IPS
 
Image Classification (F16)
100% 1048
112.3 IPS
 
Image Classification (I8)
81% 663
71.0 IPS
 
Image Segmentation (F32)
100% 1433
8.85 IPS
 
Image Segmentation (F16)
100% 1399
8.64 IPS
 
Image Segmentation (I8)
89% 1675
10.3 IPS
 
Pose Estimation (F32)
100% 496
2.01 IPS
 
Pose Estimation (F16)
100% 493
1.99 IPS
 
Pose Estimation (I8)
80% 651
2.64 IPS
 
Object Detection (F32)
100% 1415
49.7 IPS
 
Object Detection (F16)
100% 1411
49.5 IPS
 
Object Detection (I8)
52% 946
33.2 IPS
 
Face Detection (F32)
100% 1837
21.1 IPS
 
Face Detection (F16)
100% 1816
20.9 IPS
 
Face Detection (I8)
75% 1042
12.0 IPS
 
Text Classification (F32)
100% 5371
2.12 KIPS
 
Text Classification (F16)
100% 5375
2.13 KIPS
 
Machine Translation (F32)
100% 2861
440.9 IPS
 
Machine Translation (F16)
100% 2854
439.8 IPS
 

Compare

Set Baseline Geekbench 6 now available