Geekbench ML Score

6688
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 15 2024 03:22 PM
Views 4

System Information

System Information
Operating System iOS 17.5.1
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 15.05 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4236
792.6 IPS
 
Image Classification (F16)
100% 4457
834.0 IPS
 
Image Classification (I8)
99% 4099
767.0 IPS
 
Image Segmentation (F32)
100% 1994
33.3 IPS
 
Image Segmentation (F16)
100% 2247
37.5 IPS
 
Image Segmentation (I8)
100% 2204
36.8 IPS
 
Pose Estimation (F32)
100% 26791
32.4 IPS
 
Pose Estimation (F16)
100% 28555
34.6 IPS
 
Pose Estimation (I8)
100% 27993
33.9 IPS
 
Object Detection (F32)
100% 3262
243.5 IPS
 
Object Detection (F16)
100% 3835
286.3 IPS
 
Object Detection (I8)
97% 3380
252.4 IPS
 
Face Detection (F32)
100% 11388
135.4 IPS
 
Face Detection (F16)
98% 14208
168.9 IPS
 
Face Detection (I8)
97% 13617
161.9 IPS
 
Depth Estimation (F32)
100% 19847
153.9 IPS
 
Depth Estimation (F16)
100% 21730
168.5 IPS
 
Depth Estimation (I8)
37% 20064
155.6 IPS
 
Style Transfer (F32)
100% 54344
71.5 IPS
 
Style Transfer (F16)
100% 65744
86.5 IPS
 
Style Transfer (I8)
100% 64825
85.3 IPS
 
Image Super-Resolution (F32)
100% 8656
309.1 IPS
 
Image Super-Resolution (F16)
100% 8822
315.1 IPS
 
Image Super-Resolution (I8)
100% 8711
311.1 IPS
 
Text Classification (F32)
100% 1321
1.90 KIPS
 
Text Classification (F16)
100% 1400
2.01 KIPS
 
Text Classification (I8)
96% 1208
1.74 KIPS
 
Machine Translation (F32)
100% 1189
21.9 IPS
 
Machine Translation (F16)
100% 1167
21.5 IPS
 
Machine Translation (I8)
99% 911
16.8 IPS
 

Compare

Set Baseline Geekbench 6 now available