Geekbench ML Score

6781
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date September 26 2024 02:47 PM
Views 3

System Information

System Information
Operating System iOS 17.7
Model iPad Pro (11-inch 3rd generation)
Model IDiPad13,4
Motherboard J517AP
CPU Information
Name Apple M1
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.19 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 7.33 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1179
220.7 IPS
 
Image Classification (F16)
100% 6156
1.15 KIPS
 
Image Classification (I8)
99% 6284
1.18 KIPS
 
Image Segmentation (F32)
100% 820
13.7 IPS
 
Image Segmentation (F16)
100% 3992
66.7 IPS
 
Image Segmentation (I8)
100% 3979
66.5 IPS
 
Pose Estimation (F32)
100% 16422
19.9 IPS
 
Pose Estimation (F16)
100% 60687
73.5 IPS
 
Pose Estimation (I8)
100% 62889
76.2 IPS
 
Object Detection (F32)
100% 1509
112.7 IPS
 
Object Detection (F16)
100% 3838
286.6 IPS
 
Object Detection (I8)
97% 1594
119.0 IPS
 
Face Detection (F32)
100% 5808
69.1 IPS
 
Face Detection (F16)
97% 11662
138.7 IPS
 
Face Detection (I8)
96% 11654
138.6 IPS
 
Depth Estimation (F32)
100% 12108
93.9 IPS
 
Depth Estimation (F16)
100% 36417
282.4 IPS
 
Depth Estimation (I8)
37% 40007
310.3 IPS
 
Style Transfer (F32)
100% 26275
34.6 IPS
 
Style Transfer (F16)
100% 113553
149.4 IPS
 
Style Transfer (I8)
100% 116992
153.9 IPS
 
Image Super-Resolution (F32)
100% 5072
181.1 IPS
 
Image Super-Resolution (F16)
100% 17846
637.4 IPS
 
Image Super-Resolution (I8)
100% 18119
647.1 IPS
 
Text Classification (F32)
100% 1175
1.69 KIPS
 
Text Classification (F16)
100% 2319
3.33 KIPS
 
Text Classification (I8)
96% 2321
3.34 KIPS
 
Machine Translation (F32)
100% 538
9.89 IPS
 
Machine Translation (F16)
100% 1710
31.5 IPS
 
Machine Translation (I8)
99% 547
10.1 IPS
 

Compare

Set Baseline Geekbench 6 now available