Geekbench ML Score

3489
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 04 2024 08:25 PM
Views 16

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 3.49 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 7.31 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1492
279.3 IPS
 
Image Classification (F16)
100% 1899
355.3 IPS
 
Image Classification (I8)
99% 1886
352.9 IPS
 
Image Segmentation (F32)
100% 811
13.5 IPS
 
Image Segmentation (F16)
100% 797
13.3 IPS
 
Image Segmentation (I8)
100% 800
13.4 IPS
 
Pose Estimation (F32)
100% 5897
7.14 IPS
 
Pose Estimation (F16)
100% 14006
17.0 IPS
 
Pose Estimation (I8)
100% 14005
17.0 IPS
 
Object Detection (F32)
100% 1476
110.2 IPS
 
Object Detection (F16)
100% 2016
150.5 IPS
 
Object Detection (I8)
97% 1469
109.7 IPS
 
Face Detection (F32)
100% 2828
33.6 IPS
 
Face Detection (F16)
97% 4375
52.0 IPS
 
Face Detection (I8)
97% 4388
52.2 IPS
 
Depth Estimation (F32)
100% 5333
41.4 IPS
 
Depth Estimation (F16)
100% 8634
67.0 IPS
 
Depth Estimation (I8)
99% 8645
67.0 IPS
 
Style Transfer (F32)
100% 17047
22.4 IPS
 
Style Transfer (F16)
100% 26629
35.0 IPS
 
Style Transfer (I8)
100% 26629
35.0 IPS
 
Image Super-Resolution (F32)
100% 3777
134.9 IPS
 
Image Super-Resolution (F16)
100% 4983
178.0 IPS
 
Image Super-Resolution (I8)
100% 5000
178.6 IPS
 
Text Classification (F32)
100% 2101
3.02 KIPS
 
Text Classification (F16)
100% 3278
4.71 KIPS
 
Text Classification (I8)
96% 3282
4.72 KIPS
 
Machine Translation (F32)
100% 1274
23.4 IPS
 
Machine Translation (F16)
100% 1541
28.4 IPS
 
Machine Translation (I8)
99% 1264
23.3 IPS
 

Compare

Set Baseline Geekbench 6 now available