User | neotrope |
Upload Date | December 29 2024 09:30 PM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Ultra |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
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 | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1280
238.1 IPS |
|
Image Classification (HP)
|
100% |
6118
1.14 KIPS |
|
Image Classification (Q)
|
96% |
5900
1.10 KIPS |
|
Image Segmentation (SP)
|
100% |
1509
24.5 IPS |
|
Image Segmentation (HP)
|
100% |
9647
156.4 IPS |
|
Image Segmentation (Q)
|
99% |
10202
165.4 IPS |
|
Pose Estimation (SP)
|
100% |
16310
19.0 IPS |
|
Pose Estimation (HP)
|
100% |
69862
81.5 IPS |
|
Pose Estimation (Q)
|
95% |
64854
76.0 IPS |
|
Object Detection (SP)
|
100% |
1541
122.2 IPS |
|
Object Detection (HP)
|
99% |
7377
586.8 IPS |
|
Object Detection (Q)
|
91% |
6953
555.6 IPS |
|
Face Detection (SP)
|
100% |
3304
39.3 IPS |
|
Face Detection (HP)
|
100% |
14863
176.6 IPS |
|
Face Detection (Q)
|
100% |
14100
167.5 IPS |
|
Depth Estimation (SP)
|
100% |
6104
47.0 IPS |
|
Depth Estimation (HP)
|
99% |
49578
382.0 IPS |
|
Depth Estimation (Q)
|
85% |
52182
407.8 IPS |
|
Style Transfer (SP)
|
100% |
22613
29.1 IPS |
|
Style Transfer (HP)
|
100% |
119461
153.6 IPS |
|
Style Transfer (Q)
|
96% |
115270
148.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4328
159.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
24900
919.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
26896
993.1 IPS |
|
Text Classification (SP)
|
100% |
2250
3.00 KIPS |
|
Text Classification (HP)
|
100% |
3849
5.14 KIPS |
|
Text Classification (Q)
|
93% |
3835
5.15 KIPS |
|
Machine Translation (SP)
|
100% |
3212
55.3 IPS |
|
Machine Translation (HP)
|
100% |
3248
55.9 IPS |
|
Machine Translation (Q)
|
98% |
3322
57.4 IPS |