Geekbench ML Score

2995
Core ML CPU Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User WrigleyBeard
Upload Date August 17 2024 01:35 AM
Views 3

System Information

System Information
Operating System macOS 14.6.1 (Build 23G93)
Model Mac mini (Late 2020)
Model IDMacmini9,1
Motherboard Macmini9,1
CPU Information
Name Apple M1
Topology 1 Processor, 8 Cores
Identifier Apple M1
Base Frequency 3.20 GHz
Cluster 14 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 16.00 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1294
242.1 IPS
 
Image Classification (F16)
100% 1671
312.6 IPS
 
Image Classification (I8)
99% 1669
312.3 IPS
 
Image Segmentation (F32)
100% 589
9.85 IPS
 
Image Segmentation (F16)
100% 591
9.87 IPS
 
Image Segmentation (I8)
100% 607
10.1 IPS
 
Pose Estimation (F32)
100% 5629
6.82 IPS
 
Pose Estimation (F16)
100% 12994
15.7 IPS
 
Pose Estimation (I8)
100% 13005
15.7 IPS
 
Object Detection (F32)
100% 1323
98.8 IPS
 
Object Detection (F16)
100% 1758
131.2 IPS
 
Object Detection (I8)
97% 1322
98.7 IPS
 
Face Detection (F32)
100% 2395
28.5 IPS
 
Face Detection (F16)
97% 4003
47.6 IPS
 
Face Detection (I8)
97% 3945
46.9 IPS
 
Depth Estimation (F32)
100% 5212
40.4 IPS
 
Depth Estimation (F16)
100% 8162
63.3 IPS
 
Depth Estimation (I8)
99% 8169
63.3 IPS
 
Style Transfer (F32)
100% 14657
19.3 IPS
 
Style Transfer (F16)
100% 23954
31.5 IPS
 
Style Transfer (I8)
100% 24223
31.9 IPS
 
Image Super-Resolution (F32)
100% 3478
124.2 IPS
 
Image Super-Resolution (F16)
100% 4592
164.0 IPS
 
Image Super-Resolution (I8)
100% 4633
165.5 IPS
 
Text Classification (F32)
100% 2096
3.01 KIPS
 
Text Classification (F16)
100% 3363
4.83 KIPS
 
Text Classification (I8)
96% 3344
4.81 KIPS
 
Machine Translation (F32)
100% 723
13.3 IPS
 
Machine Translation (F16)
100% 873
16.1 IPS
 
Machine Translation (I8)
99% 720
13.2 IPS
 

Compare

Set Baseline Geekbench 6 now available