User | Wolfgang1756 |
Upload Date | March 28 2025 06:46 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Ultra |
System Information | |
---|---|
Operating System | macOS 15.3.2 (Build 24D2082) |
Model | Mac15,14 |
Model ID | Mac15,14 |
Motherboard | Mac15,14 |
CPU Information | |
---|---|
Name | Apple M3 Ultra |
Topology | 1 Processor, 32 Cores |
Identifier | Apple M3 Ultra |
Base Frequency | 4.05 GHz |
Cluster 1 | 24 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 256.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1691
314.4 IPS |
|
Image Classification (HP)
|
100% |
15591
2.90 KIPS |
|
Image Classification (Q)
|
97% |
17135
3.20 KIPS |
|
Image Segmentation (SP)
|
100% |
2121
34.4 IPS |
|
Image Segmentation (HP)
|
100% |
21842
354.1 IPS |
|
Image Segmentation (Q)
|
99% |
27499
445.8 IPS |
|
Pose Estimation (SP)
|
100% |
21674
25.3 IPS |
|
Pose Estimation (HP)
|
100% |
122432
142.9 IPS |
|
Pose Estimation (Q)
|
95% |
121037
141.9 IPS |
|
Object Detection (SP)
|
100% |
2159
171.2 IPS |
|
Object Detection (HP)
|
100% |
19516
1.55 KIPS |
|
Object Detection (Q)
|
91% |
19610
1.57 KIPS |
|
Face Detection (SP)
|
100% |
4445
52.8 IPS |
|
Face Detection (HP)
|
100% |
38764
460.6 IPS |
|
Face Detection (Q)
|
100% |
50423
599.1 IPS |
|
Depth Estimation (SP)
|
100% |
7529
58.0 IPS |
|
Depth Estimation (HP)
|
99% |
106675
821.9 IPS |
|
Depth Estimation (Q)
|
85% |
124034
969.8 IPS |
|
Style Transfer (SP)
|
100% |
34533
44.4 IPS |
|
Style Transfer (HP)
|
100% |
220571
283.5 IPS |
|
Style Transfer (Q)
|
96% |
216097
278.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
6736
248.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
42481
1.57 KIPS |
|
Image Super-Resolution (Q)
|
99% |
50808
1.88 KIPS |
|
Text Classification (SP)
|
100% |
2702
3.61 KIPS |
|
Text Classification (HP)
|
100% |
4865
6.49 KIPS |
|
Text Classification (Q)
|
93% |
4849
6.51 KIPS |
|
Machine Translation (SP)
|
100% |
5337
91.9 IPS |
|
Machine Translation (HP)
|
100% |
5000
86.1 IPS |
|
Machine Translation (Q)
|
98% |
5369
92.8 IPS |