Geekbench ML Score

6462
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User mrdbourke
Upload Date December 14 2023 01:12 AM
Views 19

System Information

System Information
Operating System macOS 14.1.2 (Build 23B92)
Model MacBook Pro (14-inch, 2021)
Model IDMacBookPro18,3
Motherboard MacBookPro18,3
CPU Information
Name Apple M1 Pro
Topology 1 Processor, 10 Cores
Identifier Apple M1 Pro
Base Frequency 547 MHz
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 32.00 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1088
203.5 IPS
 
Image Classification (F16)
100% 1754
328.3 IPS
 
Image Classification (I8)
99% 2620
490.3 IPS
 
Image Segmentation (F32)
100% 1251
20.9 IPS
 
Image Segmentation (F16)
100% 996
16.6 IPS
 
Image Segmentation (I8)
100% 988
16.5 IPS
 
Pose Estimation (F32)
100% 31293
37.9 IPS
 
Pose Estimation (F16)
100% 63470
76.9 IPS
 
Pose Estimation (I8)
100% 58583
70.9 IPS
 
Object Detection (F32)
100% 2815
210.2 IPS
 
Object Detection (F16)
100% 4385
327.4 IPS
 
Object Detection (I8)
97% 2701
201.7 IPS
 
Face Detection (F32)
100% 11514
136.9 IPS
 
Face Detection (F16)
97% 11289
134.2 IPS
 
Face Detection (I8)
96% 11462
136.3 IPS
 
Depth Estimation (F32)
100% 19031
147.6 IPS
 
Depth Estimation (F16)
100% 35817
277.8 IPS
 
Depth Estimation (I8)
37% 28985
224.8 IPS
 
Style Transfer (F32)
100% 50291
66.2 IPS
 
Style Transfer (F16)
100% 111421
146.6 IPS
 
Style Transfer (I8)
100% 112192
147.6 IPS
 
Image Super-Resolution (F32)
100% 7227
258.1 IPS
 
Image Super-Resolution (F16)
100% 16826
600.9 IPS
 
Image Super-Resolution (I8)
100% 17263
616.5 IPS
 
Text Classification (F32)
100% 481
691.1 IPS
 
Text Classification (F16)
100% 2026
2.91 KIPS
 
Text Classification (I8)
96% 2042
2.93 KIPS
 
Machine Translation (F32)
100% 748
13.8 IPS
 
Machine Translation (F16)
100% 2314
42.6 IPS
 
Machine Translation (I8)
99% 641
11.8 IPS
 

Compare

Set Baseline Geekbench 6 now available