Geekbench ML Score

3884
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 19 2024 02:17 AM
Views 1

System Information

System Information
Operating System iOS 18.0
Model iPad14,4
Model IDiPad14,4
Motherboard J618AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.49 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 7.36 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1363
255.0 IPS
 
Image Classification (F16)
100% 2503
468.4 IPS
 
Image Classification (I8)
99% 2503
468.4 IPS
 
Image Segmentation (F32)
100% 844
14.1 IPS
 
Image Segmentation (F16)
100% 1110
18.5 IPS
 
Image Segmentation (I8)
100% 1104
18.4 IPS
 
Pose Estimation (F32)
100% 6550
7.93 IPS
 
Pose Estimation (F16)
100% 14053
17.0 IPS
 
Pose Estimation (I8)
100% 14111
17.1 IPS
 
Object Detection (F32)
100% 1419
106.0 IPS
 
Object Detection (F16)
100% 2462
183.8 IPS
 
Object Detection (I8)
97% 1426
106.5 IPS
 
Face Detection (F32)
100% 3014
35.8 IPS
 
Face Detection (F16)
97% 5839
69.4 IPS
 
Face Detection (I8)
97% 5839
69.4 IPS
 
Depth Estimation (F32)
100% 5595
43.4 IPS
 
Depth Estimation (F16)
100% 11603
90.0 IPS
 
Depth Estimation (I8)
99% 11677
90.6 IPS
 
Style Transfer (F32)
100% 18125
23.8 IPS
 
Style Transfer (F16)
100% 27946
36.8 IPS
 
Style Transfer (I8)
100% 27928
36.7 IPS
 
Image Super-Resolution (F32)
100% 4190
149.6 IPS
 
Image Super-Resolution (F16)
100% 4925
175.9 IPS
 
Image Super-Resolution (I8)
100% 4973
177.6 IPS
 
Text Classification (F32)
100% 2072
2.98 KIPS
 
Text Classification (F16)
100% 3403
4.89 KIPS
 
Text Classification (I8)
96% 3460
4.97 KIPS
 
Machine Translation (F32)
100% 1375
25.3 IPS
 
Machine Translation (F16)
100% 1611
29.6 IPS
 
Machine Translation (I8)
99% 1366
25.1 IPS
 

Compare

Set Baseline Geekbench 6 now available