Geekbench ML Score

6756
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 08 2024 05:15 PM
Views 36

System Information

System Information
Operating System iOS 17.5
Model iPad16,6
Model IDiPad16,6
Motherboard J721AP
CPU Information
Name ARM
Topology 1 Processor, 10 Cores
Identifier ARM
Base Frequency 4.40 GHz
Cluster 14 Cores
Cluster 26 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 15.05 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4154
777.3 IPS
 
Image Classification (F16)
100% 4454
833.5 IPS
 
Image Classification (I8)
99% 4067
761.1 IPS
 
Image Segmentation (F32)
100% 2004
33.5 IPS
 
Image Segmentation (F16)
100% 2234
37.3 IPS
 
Image Segmentation (I8)
100% 2219
37.1 IPS
 
Pose Estimation (F32)
100% 27115
32.8 IPS
 
Pose Estimation (F16)
100% 28861
34.9 IPS
 
Pose Estimation (I8)
100% 28045
34.0 IPS
 
Object Detection (F32)
100% 3648
272.4 IPS
 
Object Detection (F16)
100% 3929
293.3 IPS
 
Object Detection (I8)
97% 3407
254.4 IPS
 
Face Detection (F32)
100% 11412
135.7 IPS
 
Face Detection (F16)
98% 14144
168.2 IPS
 
Face Detection (I8)
97% 13696
162.8 IPS
 
Depth Estimation (F32)
100% 19716
152.9 IPS
 
Depth Estimation (F16)
100% 22186
172.0 IPS
 
Depth Estimation (I8)
37% 19999
155.1 IPS
 
Style Transfer (F32)
100% 55342
72.8 IPS
 
Style Transfer (F16)
100% 65225
85.8 IPS
 
Style Transfer (I8)
100% 64735
85.2 IPS
 
Image Super-Resolution (F32)
100% 9088
324.6 IPS
 
Image Super-Resolution (F16)
100% 8956
319.8 IPS
 
Image Super-Resolution (I8)
100% 8019
286.4 IPS
 
Text Classification (F32)
100% 1515
2.18 KIPS
 
Text Classification (F16)
100% 1606
2.31 KIPS
 
Text Classification (I8)
96% 1221
1.75 KIPS
 
Machine Translation (F32)
100% 1090
20.1 IPS
 
Machine Translation (F16)
100% 1126
20.7 IPS
 
Machine Translation (I8)
99% 905
16.7 IPS
 

Compare

Set Baseline Geekbench 6 now available