Geekbench ML Score

7483
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date August 15 2024 06:09 PM
Views 1

System Information

System Information
Operating System iOS 18.1
Model iPad16,6
Model IDiPad16,6
Motherboard J721AP
CPU Information
Name ARM
Topology 1 Processor, 10 Cores
Identifier ARM
Base Frequency 4.41 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 15.07 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4195
785.0 IPS
 
Image Classification (F16)
100% 4483
838.9 IPS
 
Image Classification (I8)
99% 4080
763.4 IPS
 
Image Segmentation (F32)
100% 1990
33.2 IPS
 
Image Segmentation (F16)
100% 2181
36.4 IPS
 
Image Segmentation (I8)
100% 2214
37.0 IPS
 
Pose Estimation (F32)
100% 26596
32.2 IPS
 
Pose Estimation (F16)
100% 28350
34.3 IPS
 
Pose Estimation (I8)
100% 27308
33.1 IPS
 
Object Detection (F32)
100% 3381
252.4 IPS
 
Object Detection (F16)
100% 3829
285.9 IPS
 
Object Detection (I8)
97% 3242
242.1 IPS
 
Face Detection (F32)
100% 10982
130.6 IPS
 
Face Detection (F16)
98% 13741
163.4 IPS
 
Face Detection (I8)
97% 13423
159.6 IPS
 
Depth Estimation (F32)
100% 19623
152.2 IPS
 
Depth Estimation (F16)
100% 21751
168.7 IPS
 
Depth Estimation (I8)
99% 19938
154.6 IPS
 
Style Transfer (F32)
100% 55710
73.3 IPS
 
Style Transfer (F16)
100% 65067
85.6 IPS
 
Style Transfer (I8)
100% 64777
85.2 IPS
 
Image Super-Resolution (F32)
100% 9478
338.5 IPS
 
Image Super-Resolution (F16)
100% 8684
310.1 IPS
 
Image Super-Resolution (I8)
100% 9616
343.4 IPS
 
Text Classification (F32)
100% 2720
3.91 KIPS
 
Text Classification (F16)
100% 4935
7.09 KIPS
 
Text Classification (I8)
96% 5075
7.29 KIPS
 
Machine Translation (F32)
100% 1067
19.6 IPS
 
Machine Translation (F16)
100% 1123
20.7 IPS
 
Machine Translation (I8)
99% 1004
18.5 IPS
 

Compare

Set Baseline Geekbench 6 now available