Geekbench ML Score

8013
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

Upload Date August 24 2024 08:17 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% 3629
679.1 IPS
 
Image Classification (F16)
100% 6858
1.28 KIPS
 
Image Classification (I8)
99% 7431
1.39 KIPS
 
Image Segmentation (F32)
100% 1244
20.8 IPS
 
Image Segmentation (F16)
100% 3446
57.6 IPS
 
Image Segmentation (I8)
100% 3360
56.1 IPS
 
Pose Estimation (F32)
100% 31740
38.4 IPS
 
Pose Estimation (F16)
100% 61593
74.6 IPS
 
Pose Estimation (I8)
100% 62965
76.2 IPS
 
Object Detection (F32)
100% 2828
211.1 IPS
 
Object Detection (F16)
100% 4525
337.8 IPS
 
Object Detection (I8)
97% 2689
200.8 IPS
 
Face Detection (F32)
100% 11864
141.1 IPS
 
Face Detection (F16)
97% 10752
127.8 IPS
 
Face Detection (I8)
96% 10816
128.6 IPS
 
Depth Estimation (F32)
100% 19440
150.8 IPS
 
Depth Estimation (F16)
100% 36363
282.0 IPS
 
Depth Estimation (I8)
37% 35041
271.7 IPS
 
Style Transfer (F32)
100% 51261
67.4 IPS
 
Style Transfer (F16)
100% 111819
147.1 IPS
 
Style Transfer (I8)
100% 113711
149.6 IPS
 
Image Super-Resolution (F32)
100% 7701
275.0 IPS
 
Image Super-Resolution (F16)
100% 17531
626.1 IPS
 
Image Super-Resolution (I8)
100% 16693
596.2 IPS
 
Text Classification (F32)
100% 410
588.8 IPS
 
Text Classification (F16)
100% 1964
2.82 KIPS
 
Text Classification (I8)
96% 1999
2.87 KIPS
 
Machine Translation (F32)
100% 829
15.2 IPS
 
Machine Translation (F16)
100% 2491
45.8 IPS
 
Machine Translation (I8)
99% 692
12.7 IPS
 

Compare

Set Baseline Geekbench 6 now available