User | kitsunechan_2525 |
Upload Date | June 13 2025 09:34 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
Model | Mac Pro (2023) |
Model ID | Mac14,8 |
Motherboard | Mac14,8 |
CPU Information | |
---|---|
Name | Apple M2 Ultra |
Topology | 1 Processor, 24 Cores |
Identifier | Apple M2 Ultra |
Base Frequency | 3.68 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
6250
1.16 KIPS |
|
Image Classification (HP)
|
100% |
6296
1.17 KIPS |
|
Image Classification (Q)
|
96% |
5814
1.09 KIPS |
|
Image Segmentation (SP)
|
100% |
19167
310.7 IPS |
|
Image Segmentation (HP)
|
100% |
19528
316.6 IPS |
|
Image Segmentation (Q)
|
99% |
18457
299.2 IPS |
|
Pose Estimation (SP)
|
100% |
106504
124.3 IPS |
|
Pose Estimation (HP)
|
100% |
114386
133.5 IPS |
|
Pose Estimation (Q)
|
96% |
109297
128.0 IPS |
|
Object Detection (SP)
|
100% |
6236
494.6 IPS |
|
Object Detection (HP)
|
100% |
6311
500.6 IPS |
|
Object Detection (Q)
|
92% |
5888
470.0 IPS |
|
Face Detection (SP)
|
100% |
32628
387.7 IPS |
|
Face Detection (HP)
|
100% |
32332
384.2 IPS |
|
Face Detection (Q)
|
100% |
28935
343.8 IPS |
|
Depth Estimation (SP)
|
100% |
33157
255.5 IPS |
|
Depth Estimation (HP)
|
99% |
35846
276.2 IPS |
|
Depth Estimation (Q)
|
86% |
33229
259.6 IPS |
|
Style Transfer (SP)
|
100% |
194982
250.7 IPS |
|
Style Transfer (HP)
|
100% |
202187
259.9 IPS |
|
Style Transfer (Q)
|
96% |
195761
252.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
23980
885.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
25109
927.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
21825
805.9 IPS |
|
Text Classification (SP)
|
100% |
2373
3.17 KIPS |
|
Text Classification (HP)
|
100% |
4166
5.56 KIPS |
|
Text Classification (Q)
|
93% |
4127
5.54 KIPS |
|
Machine Translation (SP)
|
100% |
3341
57.5 IPS |
|
Machine Translation (HP)
|
100% |
3378
58.2 IPS |
|
Machine Translation (Q)
|
98% |
3167
54.7 IPS |