User | ___ |
Upload Date | March 18 2025 09:43 AM |
Views | 11 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.4 (Build 24E5238a) |
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 | 3.45 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1453
270.2 IPS |
|
Image Classification (HP)
|
100% |
13642
2.54 KIPS |
|
Image Classification (Q)
|
96% |
15215
2.84 KIPS |
|
Image Segmentation (SP)
|
100% |
1710
27.7 IPS |
|
Image Segmentation (HP)
|
100% |
19650
318.5 IPS |
|
Image Segmentation (Q)
|
99% |
24420
395.9 IPS |
|
Pose Estimation (SP)
|
100% |
18826
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
105142
122.7 IPS |
|
Pose Estimation (Q)
|
95% |
104962
123.0 IPS |
|
Object Detection (SP)
|
100% |
1764
139.9 IPS |
|
Object Detection (HP)
|
99% |
15393
1.22 KIPS |
|
Object Detection (Q)
|
91% |
17122
1.37 KIPS |
|
Face Detection (SP)
|
100% |
3596
42.7 IPS |
|
Face Detection (HP)
|
100% |
35347
420.0 IPS |
|
Face Detection (Q)
|
100% |
44362
527.1 IPS |
|
Depth Estimation (SP)
|
100% |
6258
48.2 IPS |
|
Depth Estimation (HP)
|
99% |
85238
656.7 IPS |
|
Depth Estimation (Q)
|
85% |
107750
842.0 IPS |
|
Style Transfer (SP)
|
100% |
28519
36.7 IPS |
|
Style Transfer (HP)
|
100% |
202521
260.3 IPS |
|
Style Transfer (Q)
|
96% |
188069
242.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5708
210.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
39772
1.47 KIPS |
|
Image Super-Resolution (Q)
|
99% |
47810
1.77 KIPS |
|
Text Classification (SP)
|
100% |
2286
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3937
5.25 KIPS |
|
Text Classification (Q)
|
93% |
3913
5.25 KIPS |
|
Machine Translation (SP)
|
100% |
4215
72.6 IPS |
|
Machine Translation (HP)
|
100% |
3917
67.5 IPS |
|
Machine Translation (Q)
|
98% |
4238
73.2 IPS |