User | egoodchild |
Upload Date | March 07 2025 02:45 AM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.3.1 (Build 24D70) |
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 | 3.67 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1473
274.0 IPS |
|
Image Classification (HP)
|
100% |
13621
2.53 KIPS |
|
Image Classification (Q)
|
96% |
16012
2.99 KIPS |
|
Image Segmentation (SP)
|
100% |
1805
29.3 IPS |
|
Image Segmentation (HP)
|
100% |
19492
316.0 IPS |
|
Image Segmentation (Q)
|
99% |
24597
398.7 IPS |
|
Pose Estimation (SP)
|
100% |
18763
21.9 IPS |
|
Pose Estimation (HP)
|
100% |
106670
124.5 IPS |
|
Pose Estimation (Q)
|
95% |
105221
123.3 IPS |
|
Object Detection (SP)
|
100% |
1860
147.6 IPS |
|
Object Detection (HP)
|
99% |
15695
1.25 KIPS |
|
Object Detection (Q)
|
91% |
17600
1.41 KIPS |
|
Face Detection (SP)
|
100% |
3763
44.7 IPS |
|
Face Detection (HP)
|
100% |
35343
419.9 IPS |
|
Face Detection (Q)
|
100% |
46674
554.6 IPS |
|
Depth Estimation (SP)
|
100% |
6347
48.9 IPS |
|
Depth Estimation (HP)
|
99% |
86309
665.0 IPS |
|
Depth Estimation (Q)
|
85% |
108221
845.7 IPS |
|
Style Transfer (SP)
|
100% |
27384
35.2 IPS |
|
Style Transfer (HP)
|
100% |
204806
263.3 IPS |
|
Style Transfer (Q)
|
96% |
192776
248.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5784
213.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
40575
1.50 KIPS |
|
Image Super-Resolution (Q)
|
99% |
48133
1.78 KIPS |
|
Text Classification (SP)
|
100% |
2292
3.06 KIPS |
|
Text Classification (HP)
|
100% |
4032
5.38 KIPS |
|
Text Classification (Q)
|
93% |
4060
5.45 KIPS |
|
Machine Translation (SP)
|
100% |
4956
85.4 IPS |
|
Machine Translation (HP)
|
100% |
4123
71.0 IPS |
|
Machine Translation (Q)
|
98% |
4437
76.7 IPS |