Geekbench ML Score

8503
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

Upload Date August 16 2024 09:06 PM
Views 2

System Information

System Information
Operating System macOS 14.6.1 (Build 23G93)
Model MacBook Pro (16-inch, 2021)
Model IDMacBookPro18,2
Motherboard MacBookPro18,2
CPU Information
Name Apple M1 Max
Topology 1 Processor, 10 Cores
Identifier Apple M1 Max
Base Frequency 3.22 GHz
Cluster 18 Cores
Cluster 22 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 64.00 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4706
880.7 IPS
 
Image Classification (F16)
100% 7199
1.35 KIPS
 
Image Classification (I8)
99% 7534
1.41 KIPS
 
Image Segmentation (F32)
100% 1550
25.9 IPS
 
Image Segmentation (F16)
100% 1476
24.6 IPS
 
Image Segmentation (I8)
100% 1462
24.4 IPS
 
Pose Estimation (F32)
100% 52347
63.4 IPS
 
Pose Estimation (F16)
100% 64743
78.4 IPS
 
Pose Estimation (I8)
100% 66354
80.4 IPS
 
Object Detection (F32)
100% 3492
260.7 IPS
 
Object Detection (F16)
100% 4327
323.0 IPS
 
Object Detection (I8)
97% 3281
244.9 IPS
 
Face Detection (F32)
100% 17199
204.5 IPS
 
Face Detection (F16)
97% 10304
122.5 IPS
 
Face Detection (I8)
96% 10594
126.0 IPS
 
Depth Estimation (F32)
100% 25122
194.8 IPS
 
Depth Estimation (F16)
100% 39266
304.5 IPS
 
Depth Estimation (I8)
37% 39869
309.2 IPS
 
Style Transfer (F32)
100% 90759
119.4 IPS
 
Style Transfer (F16)
100% 108798
143.1 IPS
 
Style Transfer (I8)
100% 115885
152.4 IPS
 
Image Super-Resolution (F32)
100% 11515
411.2 IPS
 
Image Super-Resolution (F16)
100% 17808
636.0 IPS
 
Image Super-Resolution (I8)
100% 16231
579.7 IPS
 
Text Classification (F32)
100% 799
1.15 KIPS
 
Text Classification (F16)
100% 2001
2.88 KIPS
 
Text Classification (I8)
96% 2070
2.98 KIPS
 
Machine Translation (F32)
100% 828
15.2 IPS
 
Machine Translation (F16)
100% 1507
27.7 IPS
 
Machine Translation (I8)
99% 698
12.8 IPS
 

Compare

Set Baseline Geekbench 6 now available