Geekbench ML Score

5197
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 02 2024 05:54 AM
Views 21

System Information

System Information
Operating System iOS 17.4.1
Model iPad14,6
Model IDiPad14,6
Motherboard J621AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.47 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 7.31 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3372
630.9 IPS
 
Image Classification (F16)
100% 3395
635.3 IPS
 
Image Classification (I8)
99% 3019
565.0 IPS
 
Image Segmentation (F32)
100% 1433
23.9 IPS
 
Image Segmentation (F16)
100% 1552
25.9 IPS
 
Image Segmentation (I8)
100% 1529
25.5 IPS
 
Pose Estimation (F32)
100% 23509
28.5 IPS
 
Pose Estimation (F16)
100% 24995
30.3 IPS
 
Pose Estimation (I8)
100% 24461
29.6 IPS
 
Object Detection (F32)
100% 2823
210.8 IPS
 
Object Detection (F16)
100% 2837
211.8 IPS
 
Object Detection (I8)
97% 2594
193.7 IPS
 
Face Detection (F32)
100% 9323
110.8 IPS
 
Face Detection (F16)
98% 10558
125.5 IPS
 
Face Detection (I8)
97% 10078
119.8 IPS
 
Depth Estimation (F32)
100% 16409
127.2 IPS
 
Depth Estimation (F16)
100% 17416
135.1 IPS
 
Depth Estimation (I8)
37% 15951
123.7 IPS
 
Style Transfer (F32)
100% 40344
53.1 IPS
 
Style Transfer (F16)
100% 42976
56.5 IPS
 
Style Transfer (I8)
100% 43425
57.1 IPS
 
Image Super-Resolution (F32)
100% 9599
342.8 IPS
 
Image Super-Resolution (F16)
100% 8659
309.2 IPS
 
Image Super-Resolution (I8)
100% 9630
343.9 IPS
 
Text Classification (F32)
100% 1131
1.63 KIPS
 
Text Classification (F16)
100% 761
1.09 KIPS
 
Text Classification (I8)
96% 763
1.10 KIPS
 
Machine Translation (F32)
100% 794
14.6 IPS
 
Machine Translation (F16)
100% 802
14.8 IPS
 
Machine Translation (I8)
99% 746
13.7 IPS
 

Compare

Set Baseline Geekbench 6 now available