User | Deeen |
Upload Date | September 01 2025 10:04 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.6.1 (Build 24G90) |
Model | Mac Studio (2023) |
Model ID | Mac14,14 |
Motherboard | Mac14,14 |
CPU Information | |
---|---|
Name | Apple M2 Ultra |
Topology | 1 Processor, 24 Cores |
Identifier | Apple M2 Ultra |
Base Frequency | 3.46 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1432
266.3 IPS |
|
Image Classification (HP)
|
100% |
13440
2.50 KIPS |
|
Image Classification (Q)
|
96% |
16204
3.03 KIPS |
|
Image Segmentation (SP)
|
100% |
1731
28.1 IPS |
|
Image Segmentation (HP)
|
100% |
19454
315.4 IPS |
|
Image Segmentation (Q)
|
99% |
24470
396.7 IPS |
|
Pose Estimation (SP)
|
100% |
18778
21.9 IPS |
|
Pose Estimation (HP)
|
100% |
104975
122.5 IPS |
|
Pose Estimation (Q)
|
95% |
104257
122.2 IPS |
|
Object Detection (SP)
|
100% |
1799
142.7 IPS |
|
Object Detection (HP)
|
99% |
16123
1.28 KIPS |
|
Object Detection (Q)
|
91% |
17911
1.43 KIPS |
|
Face Detection (SP)
|
100% |
3643
43.3 IPS |
|
Face Detection (HP)
|
100% |
34027
404.3 IPS |
|
Face Detection (Q)
|
100% |
45401
539.5 IPS |
|
Depth Estimation (SP)
|
100% |
6266
48.3 IPS |
|
Depth Estimation (HP)
|
99% |
86952
669.9 IPS |
|
Depth Estimation (Q)
|
85% |
108726
849.6 IPS |
|
Style Transfer (SP)
|
100% |
29155
37.5 IPS |
|
Style Transfer (HP)
|
100% |
200726
258.0 IPS |
|
Style Transfer (Q)
|
96% |
189051
244.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5934
219.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
40948
1.51 KIPS |
|
Image Super-Resolution (Q)
|
99% |
48982
1.81 KIPS |
|
Text Classification (SP)
|
100% |
2395
3.20 KIPS |
|
Text Classification (HP)
|
100% |
4131
5.51 KIPS |
|
Text Classification (Q)
|
93% |
4105
5.51 KIPS |
|
Machine Translation (SP)
|
100% |
4623
79.6 IPS |
|
Machine Translation (HP)
|
100% |
4100
70.6 IPS |
|
Machine Translation (Q)
|
98% |
4373
75.6 IPS |