User | m00m4n |
Upload Date | May 17 2025 03:47 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Ultra |
System Information | |
---|---|
Operating System | macOS 15.4.1 (Build 24E263) |
Model | Mac Studio |
Model ID | Mac13,2 |
Motherboard | Mac13,2 |
CPU Information | |
---|---|
Name | Apple M1 Ultra |
Topology | 1 Processor, 20 Cores |
Identifier | Apple M1 Ultra |
Base Frequency | 3.22 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1293
240.4 IPS |
|
Image Classification (HP)
|
100% |
6505
1.21 KIPS |
|
Image Classification (Q)
|
99% |
6926
1.29 KIPS |
|
Image Segmentation (SP)
|
100% |
1467
23.8 IPS |
|
Image Segmentation (HP)
|
100% |
8228
133.4 IPS |
|
Image Segmentation (Q)
|
100% |
8239
133.6 IPS |
|
Pose Estimation (SP)
|
100% |
15186
17.7 IPS |
|
Pose Estimation (HP)
|
100% |
69294
80.9 IPS |
|
Pose Estimation (Q)
|
94% |
65998
77.4 IPS |
|
Object Detection (SP)
|
100% |
1516
120.2 IPS |
|
Object Detection (HP)
|
99% |
7209
573.5 IPS |
|
Object Detection (Q)
|
91% |
7284
582.0 IPS |
|
Face Detection (SP)
|
100% |
3288
39.1 IPS |
|
Face Detection (HP)
|
100% |
12034
143.0 IPS |
|
Face Detection (Q)
|
100% |
13564
161.2 IPS |
|
Depth Estimation (SP)
|
100% |
5757
44.4 IPS |
|
Depth Estimation (HP)
|
99% |
45518
350.7 IPS |
|
Depth Estimation (Q)
|
97% |
48470
374.8 IPS |
|
Style Transfer (SP)
|
100% |
24308
31.2 IPS |
|
Style Transfer (HP)
|
100% |
116349
149.6 IPS |
|
Style Transfer (Q)
|
100% |
122811
157.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4187
154.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
24795
915.6 IPS |
|
Image Super-Resolution (Q)
|
98% |
26509
982.1 IPS |
|
Text Classification (SP)
|
100% |
2272
3.03 KIPS |
|
Text Classification (HP)
|
100% |
3893
5.20 KIPS |
|
Text Classification (Q)
|
93% |
3901
5.24 KIPS |
|
Machine Translation (SP)
|
100% |
3122
53.8 IPS |
|
Machine Translation (HP)
|
100% |
3636
62.6 IPS |
|
Machine Translation (Q)
|
98% |
3808
65.8 IPS |