User | benchmark_agent |
Upload Date | April 08 2025 05:35 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 14.7.4 (Build 23H420) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,9 |
Motherboard | Mac15,9 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M3 Max |
Base Frequency | 4.05 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7097
1.32 KIPS |
|
Image Classification (HP)
|
100% |
7381
1.37 KIPS |
|
Image Classification (Q)
|
97% |
5600
1.05 KIPS |
|
Image Segmentation (SP)
|
100% |
15812
256.3 IPS |
|
Image Segmentation (HP)
|
100% |
16403
265.9 IPS |
|
Image Segmentation (Q)
|
99% |
16440
266.5 IPS |
|
Pose Estimation (SP)
|
100% |
90502
105.6 IPS |
|
Pose Estimation (HP)
|
100% |
93986
109.7 IPS |
|
Pose Estimation (Q)
|
97% |
82980
97.2 IPS |
|
Object Detection (SP)
|
100% |
7121
564.9 IPS |
|
Object Detection (HP)
|
100% |
7727
612.9 IPS |
|
Object Detection (Q)
|
92% |
6404
511.1 IPS |
|
Face Detection (SP)
|
100% |
26216
311.5 IPS |
|
Face Detection (HP)
|
100% |
28748
341.6 IPS |
|
Face Detection (Q)
|
100% |
21595
256.6 IPS |
|
Depth Estimation (SP)
|
100% |
37309
287.4 IPS |
|
Depth Estimation (HP)
|
99% |
39816
306.8 IPS |
|
Depth Estimation (Q)
|
1% |
0
262.1 IPS |
|
Style Transfer (SP)
|
100% |
182026
234.0 IPS |
|
Style Transfer (HP)
|
100% |
200076
257.2 IPS |
|
Style Transfer (Q)
|
96% |
181378
234.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
24054
888.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
25141
928.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
19310
713.0 IPS |
|
Text Classification (SP)
|
100% |
511
682.1 IPS |
|
Text Classification (HP)
|
100% |
650
867.6 IPS |
|
Text Classification (Q)
|
93% |
647
867.9 IPS |
|
Machine Translation (SP)
|
100% |
1749
30.1 IPS |
|
Machine Translation (HP)
|
100% |
1748
30.1 IPS |
|
Machine Translation (Q)
|
98% |
2165
37.4 IPS |