Geekbench ML Score

2536
Core ML GPU Inference Score
Geekbench ML 0.6.0 for macOS AVX2

Result Information

Upload Date May 09 2024 02:26 AM
Views 3

System Information

System Information
Operating System macOS 14.4.1 (Build 23E224)
Model Mac Pro (Late 2019)
Model IDMacPro7,1
Motherboard Apple Inc. Mac-27AD2F918AE68F61 MacPro7,1
CPU Information
Name Intel Xeon W-3223
Topology 1 Processor, 8 Cores, 16 Threads
Identifier GenuineIntel Family 6 Model 85 Stepping 7
Base Frequency 3.50 GHz
Cluster 18 Cores
L1 Instruction Cache32.0 KB x 8
L1 Data Cache32.0 KB x 8
L2 Cache1.00 MB x 8
L3 Cache16.5 MB x 1
Memory Information
Size 192.00 GB
Transfer Rate2666 MT/s
Type DDR4
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1842
344.7 IPS
 
Image Classification (F16)
100% 1876
351.1 IPS
 
Image Classification (I8)
99% 1884
352.5 IPS
 
Image Segmentation (F32)
100% 332
5.55 IPS
 
Image Segmentation (F16)
100% 348
5.81 IPS
 
Image Segmentation (I8)
100% 355
5.92 IPS
 
Pose Estimation (F32)
100% 15131
18.3 IPS
 
Pose Estimation (F16)
100% 16434
19.9 IPS
 
Pose Estimation (I8)
100% 15449
18.7 IPS
 
Object Detection (F32)
100% 1211
90.4 IPS
 
Object Detection (F16)
100% 1298
96.9 IPS
 
Object Detection (I8)
97% 1454
108.6 IPS
 
Face Detection (F32)
100% 7386
87.8 IPS
 
Face Detection (F16)
98% 7017
83.4 IPS
 
Face Detection (I8)
97% 6885
81.9 IPS
 
Depth Estimation (F32)
100% 9129
70.8 IPS
 
Depth Estimation (F16)
100% 8514
66.0 IPS
 
Depth Estimation (I8)
37% 7859
60.9 IPS
 
Style Transfer (F32)
100% 29178
38.4 IPS
 
Style Transfer (F16)
100% 29987
39.4 IPS
 
Style Transfer (I8)
100% 30909
40.7 IPS
 
Image Super-Resolution (F32)
100% 5874
209.8 IPS
 
Image Super-Resolution (F16)
100% 4844
173.0 IPS
 
Image Super-Resolution (I8)
100% 5560
198.6 IPS
 
Text Classification (F32)
100% 278
399.5 IPS
 
Text Classification (F16)
100% 346
496.6 IPS
 
Text Classification (I8)
96% 269
387.0 IPS
 
Machine Translation (F32)
100% 290
5.33 IPS
 
Machine Translation (F16)
100% 277
5.09 IPS
 
Machine Translation (I8)
99% 294
5.41 IPS
 

Compare

Set Baseline Geekbench 6 now available