Geekbench ML Score

3892
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 18 2024 09:43 PM
Views 1

System Information

System Information
Operating System iOS 18.0
Model iPad14,8
Model IDiPad14,8
Motherboard J507AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.39 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.47 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1358
254.1 IPS
 
Image Classification (F16)
100% 2452
458.9 IPS
 
Image Classification (I8)
99% 2458
460.0 IPS
 
Image Segmentation (F32)
100% 886
14.8 IPS
 
Image Segmentation (F16)
100% 1170
19.5 IPS
 
Image Segmentation (I8)
100% 1126
18.8 IPS
 
Pose Estimation (F32)
100% 6617
8.01 IPS
 
Pose Estimation (F16)
100% 14139
17.1 IPS
 
Pose Estimation (I8)
100% 14074
17.0 IPS
 
Object Detection (F32)
100% 1446
107.9 IPS
 
Object Detection (F16)
100% 2419
180.6 IPS
 
Object Detection (I8)
97% 1439
107.4 IPS
 
Face Detection (F32)
100% 3084
36.7 IPS
 
Face Detection (F16)
97% 5899
70.1 IPS
 
Face Detection (I8)
97% 5901
70.2 IPS
 
Depth Estimation (F32)
100% 5659
43.9 IPS
 
Depth Estimation (F16)
100% 11635
90.2 IPS
 
Depth Estimation (I8)
99% 11598
89.9 IPS
 
Style Transfer (F32)
100% 18408
24.2 IPS
 
Style Transfer (F16)
100% 27830
36.6 IPS
 
Style Transfer (I8)
100% 27767
36.5 IPS
 
Image Super-Resolution (F32)
100% 4184
149.4 IPS
 
Image Super-Resolution (F16)
100% 4914
175.5 IPS
 
Image Super-Resolution (I8)
100% 4909
175.3 IPS
 
Text Classification (F32)
100% 1998
2.87 KIPS
 
Text Classification (F16)
100% 3304
4.75 KIPS
 
Text Classification (I8)
96% 3334
4.79 KIPS
 
Machine Translation (F32)
100% 1373
25.3 IPS
 
Machine Translation (F16)
100% 1634
30.1 IPS
 
Machine Translation (I8)
99% 1388
25.5 IPS
 

Compare

Set Baseline Geekbench 6 now available