Geekbench ML Score

5265
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 18 2024 09:46 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 3.48 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 GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2849
533.1 IPS
 
Image Classification (F16)
100% 2875
537.9 IPS
 
Image Classification (I8)
99% 2559
478.9 IPS
 
Image Segmentation (F32)
100% 1377
23.0 IPS
 
Image Segmentation (F16)
100% 1465
24.5 IPS
 
Image Segmentation (I8)
100% 1428
23.8 IPS
 
Pose Estimation (F32)
100% 21268
25.8 IPS
 
Pose Estimation (F16)
100% 22664
27.4 IPS
 
Pose Estimation (I8)
100% 21866
26.5 IPS
 
Object Detection (F32)
100% 2682
200.2 IPS
 
Object Detection (F16)
100% 2619
195.5 IPS
 
Object Detection (I8)
97% 2464
184.0 IPS
 
Face Detection (F32)
100% 8573
101.9 IPS
 
Face Detection (F16)
98% 9447
112.3 IPS
 
Face Detection (I8)
97% 9256
110.1 IPS
 
Depth Estimation (F32)
100% 15296
118.6 IPS
 
Depth Estimation (F16)
100% 16182
125.5 IPS
 
Depth Estimation (I8)
99% 14524
112.6 IPS
 
Style Transfer (F32)
100% 37173
48.9 IPS
 
Style Transfer (F16)
100% 42876
56.4 IPS
 
Style Transfer (I8)
100% 42613
56.1 IPS
 
Image Super-Resolution (F32)
100% 6946
248.0 IPS
 
Image Super-Resolution (F16)
100% 6815
243.4 IPS
 
Image Super-Resolution (I8)
100% 6419
229.2 IPS
 
Text Classification (F32)
100% 2006
2.88 KIPS
 
Text Classification (F16)
100% 3317
4.77 KIPS
 
Text Classification (I8)
96% 3319
4.77 KIPS
 
Machine Translation (F32)
100% 789
14.5 IPS
 
Machine Translation (F16)
100% 763
14.0 IPS
 
Machine Translation (I8)
99% 541
9.96 IPS
 

Compare

Set Baseline Geekbench 6 now available