User | anthonynelzin |
Upload Date | March 13 2025 09:40 AM |
Views | 10 |
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, 28 Cores |
Identifier | Apple M3 Ultra |
Base Frequency | 4.05 GHz |
Cluster 1 | 20 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 96.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1725
320.9 IPS |
|
Image Classification (HP)
|
100% |
15341
2.85 KIPS |
|
Image Classification (Q)
|
97% |
16709
3.12 KIPS |
|
Image Segmentation (SP)
|
100% |
2144
34.8 IPS |
|
Image Segmentation (HP)
|
100% |
21791
353.3 IPS |
|
Image Segmentation (Q)
|
99% |
26885
435.8 IPS |
|
Pose Estimation (SP)
|
100% |
21796
25.4 IPS |
|
Pose Estimation (HP)
|
100% |
120353
140.4 IPS |
|
Pose Estimation (Q)
|
95% |
119323
139.9 IPS |
|
Object Detection (SP)
|
100% |
2207
175.1 IPS |
|
Object Detection (HP)
|
100% |
17350
1.38 KIPS |
|
Object Detection (Q)
|
91% |
18578
1.48 KIPS |
|
Face Detection (SP)
|
100% |
4721
56.1 IPS |
|
Face Detection (HP)
|
100% |
37981
451.3 IPS |
|
Face Detection (Q)
|
100% |
48845
580.4 IPS |
|
Depth Estimation (SP)
|
100% |
8198
63.2 IPS |
|
Depth Estimation (HP)
|
99% |
102013
785.9 IPS |
|
Depth Estimation (Q)
|
85% |
115250
901.1 IPS |
|
Style Transfer (SP)
|
100% |
34221
44.0 IPS |
|
Style Transfer (HP)
|
100% |
218301
280.6 IPS |
|
Style Transfer (Q)
|
96% |
211876
273.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
7027
259.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
37263
1.38 KIPS |
|
Image Super-Resolution (Q)
|
99% |
48996
1.81 KIPS |
|
Text Classification (SP)
|
100% |
2722
3.63 KIPS |
|
Text Classification (HP)
|
100% |
4926
6.58 KIPS |
|
Text Classification (Q)
|
93% |
4902
6.58 KIPS |
|
Machine Translation (SP)
|
100% |
5727
98.7 IPS |
|
Machine Translation (HP)
|
100% |
5028
86.6 IPS |
|
Machine Translation (Q)
|
98% |
5423
93.7 IPS |