Geekbench ML Score

728
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date August 15 2024 03:09 PM
Views 1

System Information

System Information
Operating System iOS 17.6.1
Model iPad Air (3rd generation)
Model IDiPad11,3
Motherboard J217AP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
Cluster 12 Cores
Cluster 24 Cores
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 2.84 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 320
59.9 IPS
 
Image Classification (F16)
100% 547
102.3 IPS
 
Image Classification (I8)
99% 557
104.2 IPS
 
Image Segmentation (F32)
100% 242
4.05 IPS
 
Image Segmentation (F16)
100% 296
4.94 IPS
 
Image Segmentation (I8)
100% 296
4.94 IPS
 
Pose Estimation (F32)
100% 1105
1.34 IPS
 
Pose Estimation (F16)
100% 704
0.85 IPS
 
Pose Estimation (I8)
100% 907
1.10 IPS
 
Object Detection (F32)
100% 373
27.9 IPS
 
Object Detection (F16)
100% 628
46.9 IPS
 
Object Detection (I8)
97% 362
27.1 IPS
 
Face Detection (F32)
100% 749
8.91 IPS
 
Face Detection (F16)
97% 1468
17.5 IPS
 
Face Detection (I8)
96% 1482
17.6 IPS
 
Depth Estimation (F32)
100% 856
6.64 IPS
 
Depth Estimation (F16)
100% 1688
13.1 IPS
 
Depth Estimation (I8)
99% 1661
12.9 IPS
 
Style Transfer (F32)
100% 2336
3.07 IPS
 
Style Transfer (F16)
100% 4454
5.86 IPS
 
Style Transfer (I8)
100% 4139
5.44 IPS
 
Image Super-Resolution (F32)
100% 744
26.6 IPS
 
Image Super-Resolution (F16)
100% 980
35.0 IPS
 
Image Super-Resolution (I8)
100% 974
34.8 IPS
 
Text Classification (F32)
100% 265
380.7 IPS
 
Text Classification (F16)
100% 524
753.1 IPS
 
Text Classification (I8)
96% 524
752.6 IPS
 
Machine Translation (F32)
100% 373
6.86 IPS
 
Machine Translation (F16)
100% 509
9.36 IPS
 
Machine Translation (I8)
99% 372
6.84 IPS
 

Compare

Set Baseline Geekbench 6 now available