User | mamiyoshi |
Upload Date | March 25 2025 01:48 AM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Ultra |
System Information | |
---|---|
Operating System | macOS 15.4 (Build 24E5238a) |
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% |
1256
233.6 IPS |
|
Image Classification (HP)
|
100% |
6556
1.22 KIPS |
|
Image Classification (Q)
|
96% |
6266
1.17 KIPS |
|
Image Segmentation (SP)
|
100% |
1456
23.6 IPS |
|
Image Segmentation (HP)
|
100% |
9805
158.9 IPS |
|
Image Segmentation (Q)
|
99% |
10462
169.6 IPS |
|
Pose Estimation (SP)
|
100% |
15299
17.9 IPS |
|
Pose Estimation (HP)
|
100% |
70997
82.8 IPS |
|
Pose Estimation (Q)
|
95% |
67027
78.6 IPS |
|
Object Detection (SP)
|
100% |
1509
119.7 IPS |
|
Object Detection (HP)
|
99% |
7784
619.2 IPS |
|
Object Detection (Q)
|
91% |
7245
578.9 IPS |
|
Face Detection (SP)
|
100% |
3256
38.7 IPS |
|
Face Detection (HP)
|
100% |
16209
192.6 IPS |
|
Face Detection (Q)
|
100% |
13358
158.7 IPS |
|
Depth Estimation (SP)
|
100% |
5675
43.7 IPS |
|
Depth Estimation (HP)
|
99% |
51114
393.8 IPS |
|
Depth Estimation (Q)
|
85% |
54185
423.4 IPS |
|
Style Transfer (SP)
|
100% |
24311
31.3 IPS |
|
Style Transfer (HP)
|
100% |
120281
154.6 IPS |
|
Style Transfer (Q)
|
96% |
115948
149.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4322
159.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
24922
920.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
26907
993.6 IPS |
|
Text Classification (SP)
|
100% |
2192
2.93 KIPS |
|
Text Classification (HP)
|
100% |
3745
5.00 KIPS |
|
Text Classification (Q)
|
93% |
3707
4.98 KIPS |
|
Machine Translation (SP)
|
100% |
3240
55.8 IPS |
|
Machine Translation (HP)
|
100% |
3630
62.5 IPS |
|
Machine Translation (Q)
|
98% |
3776
65.3 IPS |