Geekbench ML Score

1429
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 03 2023 08:35 PM
Views 2

System Information

System Information
Operating System iOS 17.1.2
Model iPhone16,1
Model IDiPhone16,1
Motherboard D83AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.76 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.50 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1095
117.4 IPS
 
Image Classification (F16)
100% 1073
115.0 IPS
 
Image Classification (I8)
81% 621
66.6 IPS
 
Image Segmentation (F32)
100% 1454
8.98 IPS
 
Image Segmentation (F16)
100% 1442
8.91 IPS
 
Image Segmentation (I8)
89% 1668
10.3 IPS
 
Pose Estimation (F32)
100% 525
2.12 IPS
 
Pose Estimation (F16)
100% 521
2.11 IPS
 
Pose Estimation (I8)
80% 679
2.75 IPS
 
Object Detection (F32)
100% 1489
52.2 IPS
 
Object Detection (F16)
100% 1493
52.4 IPS
 
Object Detection (I8)
52% 959
33.6 IPS
 
Face Detection (F32)
100% 1913
22.0 IPS
 
Face Detection (F16)
100% 1891
21.7 IPS
 
Face Detection (I8)
75% 1042
12.0 IPS
 
Text Classification (F32)
100% 5388
2.13 KIPS
 
Text Classification (F16)
100% 5343
2.11 KIPS
 
Machine Translation (F32)
100% 2847
438.7 IPS
 
Machine Translation (F16)
100% 2852
439.6 IPS
 

Compare

Set Baseline Geekbench 6 now available