Geekbench ML Score

6844
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date September 02 2024 07:01 PM
Views 1

System Information

System Information
Operating System iOS 18.0
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 7.37 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1234
230.9 IPS
 
Image Classification (F16)
100% 6011
1.12 KIPS
 
Image Classification (I8)
99% 6315
1.18 KIPS
 
Image Segmentation (F32)
100% 805
13.4 IPS
 
Image Segmentation (F16)
100% 1104
18.4 IPS
 
Image Segmentation (I8)
100% 1103
18.4 IPS
 
Pose Estimation (F32)
100% 16109
19.5 IPS
 
Pose Estimation (F16)
100% 63153
76.5 IPS
 
Pose Estimation (I8)
100% 63233
76.6 IPS
 
Object Detection (F32)
100% 1542
115.1 IPS
 
Object Detection (F16)
100% 3925
293.0 IPS
 
Object Detection (I8)
97% 1489
111.2 IPS
 
Face Detection (F32)
100% 6496
77.2 IPS
 
Face Detection (F16)
97% 11751
139.7 IPS
 
Face Detection (I8)
96% 11853
140.9 IPS
 
Depth Estimation (F32)
100% 12697
98.5 IPS
 
Depth Estimation (F16)
100% 39972
310.0 IPS
 
Depth Estimation (I8)
37% 44489
345.0 IPS
 
Style Transfer (F32)
100% 29045
38.2 IPS
 
Style Transfer (F16)
100% 116165
152.8 IPS
 
Style Transfer (I8)
100% 121141
159.4 IPS
 
Image Super-Resolution (F32)
100% 6876
245.5 IPS
 
Image Super-Resolution (F16)
100% 22893
817.6 IPS
 
Image Super-Resolution (I8)
100% 23326
833.0 IPS
 
Text Classification (F32)
100% 2116
3.04 KIPS
 
Text Classification (F16)
100% 3258
4.68 KIPS
 
Text Classification (I8)
96% 3532
5.08 KIPS
 
Machine Translation (F32)
100% 512
9.42 IPS
 
Machine Translation (F16)
100% 1812
33.3 IPS
 
Machine Translation (I8)
99% 624
11.5 IPS
 

Compare

Set Baseline Geekbench 6 now available