Geekbench ML Score

8357
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User idanbo
Upload Date March 28 2024 04:48 AM
Views 5
Notes MacBook Pro (14-inch, M3, Nov 2023)/M3 8Core CPU/10Core GPU

System Information

System Information
Operating System macOS 14.4.1 (Build 23E224)
Model MacBook Pro (14-inch, Nov 2023)
Model IDMac15,3
Motherboard Mac15,3
CPU Information
Name Apple M3
Topology 1 Processor, 8 Cores
Identifier Apple M3
Base Frequency 4.05 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 8.00 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4125
771.8 IPS
 
Image Classification (F16)
100% 7213
1.35 KIPS
 
Image Classification (I8)
99% 8078
1.51 KIPS
 
Image Segmentation (F32)
100% 1802
30.1 IPS
 
Image Segmentation (F16)
100% 2096
35.0 IPS
 
Image Segmentation (I8)
100% 2149
35.9 IPS
 
Pose Estimation (F32)
100% 23841
28.9 IPS
 
Pose Estimation (F16)
100% 96951
117.4 IPS
 
Pose Estimation (I8)
100% 97805
118.4 IPS
 
Object Detection (F32)
100% 3120
233.0 IPS
 
Object Detection (F16)
100% 5004
373.6 IPS
 
Object Detection (I8)
97% 3111
232.3 IPS
 
Face Detection (F32)
100% 10457
124.3 IPS
 
Face Detection (F16)
97% 12730
151.4 IPS
 
Face Detection (I8)
96% 12825
152.5 IPS
 
Depth Estimation (F32)
100% 18332
142.2 IPS
 
Depth Estimation (F16)
100% 42467
329.3 IPS
 
Depth Estimation (I8)
37% 47462
368.1 IPS
 
Style Transfer (F32)
100% 50351
66.2 IPS
 
Style Transfer (F16)
100% 148743
195.7 IPS
 
Style Transfer (I8)
100% 148384
195.2 IPS
 
Image Super-Resolution (F32)
100% 8651
309.0 IPS
 
Image Super-Resolution (F16)
100% 20977
749.1 IPS
 
Image Super-Resolution (I8)
100% 20373
727.6 IPS
 
Text Classification (F32)
100% 565
812.7 IPS
 
Text Classification (F16)
100% 689
989.6 IPS
 
Text Classification (I8)
96% 688
988.4 IPS
 
Machine Translation (F32)
100% 1036
19.1 IPS
 
Machine Translation (F16)
100% 3411
62.8 IPS
 
Machine Translation (I8)
99% 874
16.1 IPS
 

Compare

Set Baseline Geekbench 6 now available