User | Toda |
Upload Date | September 08 2025 10:56 AM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.6.1 (Build 24G90) |
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 | 3.32 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 192.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
5826
1.08 KIPS |
|
Image Classification (HP)
|
100% |
6035
1.12 KIPS |
|
Image Classification (Q)
|
96% |
5544
1.04 KIPS |
|
Image Segmentation (SP)
|
100% |
20138
326.5 IPS |
|
Image Segmentation (HP)
|
100% |
20925
339.2 IPS |
|
Image Segmentation (Q)
|
99% |
19870
322.1 IPS |
|
Pose Estimation (SP)
|
100% |
134060
156.4 IPS |
|
Pose Estimation (HP)
|
100% |
146448
170.9 IPS |
|
Pose Estimation (Q)
|
96% |
138592
162.3 IPS |
|
Object Detection (SP)
|
100% |
5979
474.2 IPS |
|
Object Detection (HP)
|
100% |
6165
489.0 IPS |
|
Object Detection (Q)
|
92% |
5680
453.4 IPS |
|
Face Detection (SP)
|
100% |
31385
372.9 IPS |
|
Face Detection (HP)
|
100% |
29993
356.4 IPS |
|
Face Detection (Q)
|
100% |
27442
326.1 IPS |
|
Depth Estimation (SP)
|
100% |
33363
257.0 IPS |
|
Depth Estimation (HP)
|
99% |
35830
276.0 IPS |
|
Depth Estimation (Q)
|
86% |
33043
258.1 IPS |
|
Style Transfer (SP)
|
100% |
219776
282.5 IPS |
|
Style Transfer (HP)
|
100% |
227611
292.6 IPS |
|
Style Transfer (Q)
|
96% |
220173
284.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
24095
889.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
25706
949.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
21749
803.1 IPS |
|
Text Classification (SP)
|
100% |
2233
2.98 KIPS |
|
Text Classification (HP)
|
100% |
3855
5.15 KIPS |
|
Text Classification (Q)
|
93% |
3804
5.11 KIPS |
|
Machine Translation (SP)
|
100% |
3354
57.8 IPS |
|
Machine Translation (HP)
|
100% |
3424
59.0 IPS |
|
Machine Translation (Q)
|
98% |
3364
58.1 IPS |