Geekbench ML Score

11444
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User mweinbach
Upload Date December 08 2023 04:47 PM
Views 5

System Information

System Information
Operating System macOS 14.2 (Build 23C64)
Model MacBook Pro (16-inch, Nov 2023)
Model IDMac15,9
Motherboard Mac15,9
CPU Information
Name Apple M3 Max
Topology 1 Processor, 16 Cores
Identifier Apple M3 Max
Base Frequency 4.05 GHz
Cluster 112 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 128.00 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6642
1.24 KIPS
 
Image Classification (F16)
100% 7567
1.42 KIPS
 
Image Classification (I8)
99% 7184
1.34 KIPS
 
Image Segmentation (F32)
100% 2355
39.3 IPS
 
Image Segmentation (F16)
100% 2145
35.8 IPS
 
Image Segmentation (I8)
100% 2105
35.2 IPS
 
Pose Estimation (F32)
100% 83693
101.3 IPS
 
Pose Estimation (F16)
100% 93437
113.1 IPS
 
Pose Estimation (I8)
100% 94403
114.3 IPS
 
Object Detection (F32)
100% 4885
364.7 IPS
 
Object Detection (F16)
100% 4953
369.8 IPS
 
Object Detection (I8)
97% 5024
375.1 IPS
 
Face Detection (F32)
100% 24782
294.7 IPS
 
Face Detection (F16)
97% 15218
180.9 IPS
 
Face Detection (I8)
96% 14228
169.2 IPS
 
Depth Estimation (F32)
100% 34759
269.6 IPS
 
Depth Estimation (F16)
100% 56395
437.3 IPS
 
Depth Estimation (I8)
37% 32487
251.9 IPS
 
Style Transfer (F32)
100% 163669
215.3 IPS
 
Style Transfer (F16)
100% 137595
181.0 IPS
 
Style Transfer (I8)
100% 133849
176.1 IPS
 
Image Super-Resolution (F32)
100% 16215
579.1 IPS
 
Image Super-Resolution (F16)
100% 16048
573.1 IPS
 
Image Super-Resolution (I8)
100% 18589
663.9 IPS
 
Text Classification (F32)
100% 959
1.38 KIPS
 
Text Classification (F16)
100% 3361
4.83 KIPS
 
Text Classification (I8)
96% 3602
5.18 KIPS
 
Machine Translation (F32)
100% 1007
18.5 IPS
 
Machine Translation (F16)
100% 3083
56.7 IPS
 
Machine Translation (I8)
99% 925
17.0 IPS
 

Compare

Set Baseline Geekbench 6 now available