User | kitsunechan_2525 |
Upload Date | June 13 2025 09:35 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
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 | 3.68 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1473
273.8 IPS |
|
Image Classification (HP)
|
100% |
13649
2.54 KIPS |
|
Image Classification (Q)
|
96% |
6739
1.26 KIPS |
|
Image Segmentation (SP)
|
100% |
1747
28.3 IPS |
|
Image Segmentation (HP)
|
100% |
19474
315.7 IPS |
|
Image Segmentation (Q)
|
99% |
24440
396.2 IPS |
|
Pose Estimation (SP)
|
100% |
18236
21.3 IPS |
|
Pose Estimation (HP)
|
100% |
104902
122.4 IPS |
|
Pose Estimation (Q)
|
95% |
103774
121.6 IPS |
|
Object Detection (SP)
|
100% |
1819
144.3 IPS |
|
Object Detection (HP)
|
99% |
15873
1.26 KIPS |
|
Object Detection (Q)
|
91% |
17532
1.40 KIPS |
|
Face Detection (SP)
|
100% |
3645
43.3 IPS |
|
Face Detection (HP)
|
100% |
35240
418.7 IPS |
|
Face Detection (Q)
|
100% |
45730
543.4 IPS |
|
Depth Estimation (SP)
|
100% |
6225
48.0 IPS |
|
Depth Estimation (HP)
|
99% |
85645
659.8 IPS |
|
Depth Estimation (Q)
|
85% |
108532
848.1 IPS |
|
Style Transfer (SP)
|
100% |
28910
37.2 IPS |
|
Style Transfer (HP)
|
100% |
202750
260.6 IPS |
|
Style Transfer (Q)
|
96% |
189921
245.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
5737
211.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
40409
1.49 KIPS |
|
Image Super-Resolution (Q)
|
99% |
47719
1.76 KIPS |
|
Text Classification (SP)
|
100% |
2366
3.16 KIPS |
|
Text Classification (HP)
|
100% |
4153
5.54 KIPS |
|
Text Classification (Q)
|
93% |
4154
5.57 KIPS |
|
Machine Translation (SP)
|
100% |
4347
74.9 IPS |
|
Machine Translation (HP)
|
100% |
4098
70.6 IPS |
|
Machine Translation (Q)
|
98% |
4369
75.5 IPS |