Geekbench ML Score

5452
Core ML GPU Inference Score
Geekbench ML 0.6.0 for macOS AVX2

Result Information

User Hais
Upload Date August 16 2024 03:29 PM
Views 2

System Information

System Information
Operating System macOS 14.5 (Build 23F79)
Model MacPro7,1
Model IDMacPro7,1
Motherboard Acidanthera Mac-27AD2F918AE68F61 MacPro7,1
CPU Information
Name Intel Core i9-10900K
Topology 1 Processor, 10 Cores, 20 Threads
Identifier GenuineIntel Family 6 Model 165 Stepping 5
Base Frequency 3.70 GHz
Cluster 110 Cores
L1 Instruction Cache32.0 KB x 10
L1 Data Cache32.0 KB x 10
L2 Cache256 KB x 10
L3 Cache20.0 MB x 1
Memory Information
Size 32.00 GB
Type RAM
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4306
805.8 IPS
 
Image Classification (F16)
100% 4370
817.8 IPS
 
Image Classification (I8)
99% 4354
814.8 IPS
 
Image Segmentation (F32)
100% 575
9.60 IPS
 
Image Segmentation (F16)
100% 576
9.62 IPS
 
Image Segmentation (I8)
100% 569
9.51 IPS
 
Pose Estimation (F32)
100% 90446
109.5 IPS
 
Pose Estimation (F16)
100% 80215
97.1 IPS
 
Pose Estimation (I8)
100% 80027
96.9 IPS
 
Object Detection (F32)
100% 2132
159.2 IPS
 
Object Detection (F16)
100% 2070
154.6 IPS
 
Object Detection (I8)
97% 1692
126.3 IPS
 
Face Detection (F32)
100% 13373
159.0 IPS
 
Face Detection (F16)
98% 13329
158.5 IPS
 
Face Detection (I8)
97% 13538
161.0 IPS
 
Depth Estimation (F32)
100% 21590
167.4 IPS
 
Depth Estimation (F16)
100% 30171
234.0 IPS
 
Depth Estimation (I8)
37% 22859
177.3 IPS
 
Style Transfer (F32)
100% 86785
114.2 IPS
 
Style Transfer (F16)
100% 85217
112.1 IPS
 
Style Transfer (I8)
100% 85577
112.6 IPS
 
Image Super-Resolution (F32)
100% 5803
207.3 IPS
 
Image Super-Resolution (F16)
100% 6917
247.0 IPS
 
Image Super-Resolution (I8)
100% 6789
242.5 IPS
 
Text Classification (F32)
100% 391
562.4 IPS
 
Text Classification (F16)
100% 359
515.7 IPS
 
Text Classification (I8)
96% 337
484.3 IPS
 
Machine Translation (F32)
100% 851
15.7 IPS
 
Machine Translation (F16)
100% 877
16.1 IPS
 
Machine Translation (I8)
99% 854
15.7 IPS
 

Compare

Set Baseline Geekbench 6 now available