User | Gonfonix |
Upload Date | November 30 2024 11:51 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B91) |
Model | Mac Pro (2023) |
Model ID | Mac14,8 |
Motherboard | Mac14,8 |
CPU Information | |
---|---|
Name | Apple M2 Ultra |
Topology | 1 Processor, 24 Cores |
Identifier | Apple M2 Ultra |
Base Frequency | 3.66 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 192.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1463
272.0 IPS |
|
Image Classification (HP)
|
100% |
13476
2.51 KIPS |
|
Image Classification (Q)
|
96% |
15763
2.94 KIPS |
|
Image Segmentation (SP)
|
100% |
1814
29.4 IPS |
|
Image Segmentation (HP)
|
100% |
19576
317.3 IPS |
|
Image Segmentation (Q)
|
99% |
24550
398.0 IPS |
|
Pose Estimation (SP)
|
100% |
19076
22.3 IPS |
|
Pose Estimation (HP)
|
100% |
104900
122.4 IPS |
|
Pose Estimation (Q)
|
95% |
103025
120.8 IPS |
|
Object Detection (SP)
|
100% |
1852
146.9 IPS |
|
Object Detection (HP)
|
99% |
15803
1.26 KIPS |
|
Object Detection (Q)
|
91% |
17595
1.41 KIPS |
|
Face Detection (SP)
|
100% |
3848
45.7 IPS |
|
Face Detection (HP)
|
100% |
35655
423.7 IPS |
|
Face Detection (Q)
|
100% |
45734
543.4 IPS |
|
Depth Estimation (SP)
|
100% |
6403
49.3 IPS |
|
Depth Estimation (HP)
|
99% |
85446
658.3 IPS |
|
Depth Estimation (Q)
|
85% |
106167
829.6 IPS |
|
Style Transfer (SP)
|
100% |
27131
34.9 IPS |
|
Style Transfer (HP)
|
100% |
201631
259.2 IPS |
|
Style Transfer (Q)
|
96% |
189624
244.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
6027
222.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
40272
1.49 KIPS |
|
Image Super-Resolution (Q)
|
99% |
47802
1.77 KIPS |
|
Text Classification (SP)
|
100% |
2296
3.06 KIPS |
|
Text Classification (HP)
|
100% |
4041
5.39 KIPS |
|
Text Classification (Q)
|
93% |
4018
5.39 KIPS |
|
Machine Translation (SP)
|
100% |
4946
85.2 IPS |
|
Machine Translation (HP)
|
100% |
3520
60.6 IPS |
|
Machine Translation (Q)
|
98% |
3707
64.1 IPS |