Geekbench ML Score

8003
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

Upload Date August 24 2024 06:43 PM
Views 2

System Information

System Information
Operating System macOS 14.5 (Build 23F79)
Model MacBook Pro (16-inch, 2021)
Model IDMacBookPro18,1
Motherboard MacBookPro18,1
CPU Information
Name Apple M1 Pro
Topology 1 Processor, 10 Cores
Identifier Apple M1 Pro
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 16.00 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3624
678.1 IPS
 
Image Classification (F16)
100% 7026
1.31 KIPS
 
Image Classification (I8)
99% 7168
1.34 KIPS
 
Image Segmentation (F32)
100% 1230
20.5 IPS
 
Image Segmentation (F16)
100% 3395
56.7 IPS
 
Image Segmentation (I8)
100% 3538
59.1 IPS
 
Pose Estimation (F32)
100% 31147
37.7 IPS
 
Pose Estimation (F16)
100% 61656
74.7 IPS
 
Pose Estimation (I8)
100% 62761
76.0 IPS
 
Object Detection (F32)
100% 2857
213.3 IPS
 
Object Detection (F16)
100% 4417
329.7 IPS
 
Object Detection (I8)
97% 2617
195.4 IPS
 
Face Detection (F32)
100% 11759
139.8 IPS
 
Face Detection (F16)
97% 10786
128.2 IPS
 
Face Detection (I8)
96% 10766
128.0 IPS
 
Depth Estimation (F32)
100% 19085
148.0 IPS
 
Depth Estimation (F16)
100% 36027
279.4 IPS
 
Depth Estimation (I8)
37% 36660
284.3 IPS
 
Style Transfer (F32)
100% 50810
66.8 IPS
 
Style Transfer (F16)
100% 110960
146.0 IPS
 
Style Transfer (I8)
100% 116508
153.3 IPS
 
Image Super-Resolution (F32)
100% 8383
299.4 IPS
 
Image Super-Resolution (F16)
100% 17499
625.0 IPS
 
Image Super-Resolution (I8)
100% 17273
616.9 IPS
 
Text Classification (F32)
100% 473
679.4 IPS
 
Text Classification (F16)
100% 1851
2.66 KIPS
 
Text Classification (I8)
96% 1883
2.71 KIPS
 
Machine Translation (F32)
100% 777
14.3 IPS
 
Machine Translation (F16)
100% 2360
43.4 IPS
 
Machine Translation (I8)
99% 676
12.4 IPS
 

Compare

Set Baseline Geekbench 6 now available