User | anthonynelzin |
Upload Date | March 13 2025 09:37 AM |
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, 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% |
1714
318.8 IPS |
|
Image Classification (HP)
|
100% |
15248
2.84 KIPS |
|
Image Classification (Q)
|
97% |
16767
3.13 KIPS |
|
Image Segmentation (SP)
|
100% |
2146
34.8 IPS |
|
Image Segmentation (HP)
|
100% |
21529
349.0 IPS |
|
Image Segmentation (Q)
|
99% |
26533
430.1 IPS |
|
Pose Estimation (SP)
|
100% |
21544
25.1 IPS |
|
Pose Estimation (HP)
|
100% |
120463
140.6 IPS |
|
Pose Estimation (Q)
|
95% |
118583
139.0 IPS |
|
Object Detection (SP)
|
100% |
2206
175.0 IPS |
|
Object Detection (HP)
|
100% |
17479
1.39 KIPS |
|
Object Detection (Q)
|
91% |
17993
1.44 KIPS |
|
Face Detection (SP)
|
100% |
4715
56.0 IPS |
|
Face Detection (HP)
|
100% |
38025
451.8 IPS |
|
Face Detection (Q)
|
100% |
48899
581.0 IPS |
|
Depth Estimation (SP)
|
100% |
8186
63.1 IPS |
|
Depth Estimation (HP)
|
99% |
101883
784.9 IPS |
|
Depth Estimation (Q)
|
85% |
116184
908.4 IPS |
|
Style Transfer (SP)
|
100% |
34205
44.0 IPS |
|
Style Transfer (HP)
|
100% |
218826
281.3 IPS |
|
Style Transfer (Q)
|
96% |
212892
274.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
7036
259.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
37556
1.39 KIPS |
|
Image Super-Resolution (Q)
|
99% |
49182
1.82 KIPS |
|
Text Classification (SP)
|
100% |
2738
3.65 KIPS |
|
Text Classification (HP)
|
100% |
4982
6.65 KIPS |
|
Text Classification (Q)
|
93% |
4953
6.65 KIPS |
|
Machine Translation (SP)
|
100% |
5738
98.8 IPS |
|
Machine Translation (HP)
|
100% |
4971
85.6 IPS |
|
Machine Translation (Q)
|
98% |
5426
93.8 IPS |