User | tlonergan02 |
Upload Date | November 04 2024 05:13 AM |
Views | 25 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
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 | 3.47 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1450
269.6 IPS |
|
Image Classification (HP)
|
100% |
13382
2.49 KIPS |
|
Image Classification (Q)
|
96% |
15862
2.96 KIPS |
|
Image Segmentation (SP)
|
100% |
1771
28.7 IPS |
|
Image Segmentation (HP)
|
100% |
19633
318.3 IPS |
|
Image Segmentation (Q)
|
99% |
24492
397.0 IPS |
|
Pose Estimation (SP)
|
100% |
18995
22.2 IPS |
|
Pose Estimation (HP)
|
100% |
105633
123.3 IPS |
|
Pose Estimation (Q)
|
95% |
105129
123.2 IPS |
|
Object Detection (SP)
|
100% |
1823
144.6 IPS |
|
Object Detection (HP)
|
99% |
15579
1.24 KIPS |
|
Object Detection (Q)
|
91% |
17456
1.39 KIPS |
|
Face Detection (SP)
|
100% |
3745
44.5 IPS |
|
Face Detection (HP)
|
100% |
34004
404.0 IPS |
|
Face Detection (Q)
|
100% |
46644
554.2 IPS |
|
Depth Estimation (SP)
|
100% |
6326
48.7 IPS |
|
Depth Estimation (HP)
|
99% |
86108
663.4 IPS |
|
Depth Estimation (Q)
|
85% |
107847
842.8 IPS |
|
Style Transfer (SP)
|
100% |
27192
35.0 IPS |
|
Style Transfer (HP)
|
100% |
202773
260.7 IPS |
|
Style Transfer (Q)
|
96% |
194334
250.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5881
217.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
40093
1.48 KIPS |
|
Image Super-Resolution (Q)
|
99% |
48284
1.78 KIPS |
|
Text Classification (SP)
|
100% |
2313
3.09 KIPS |
|
Text Classification (HP)
|
100% |
4008
5.35 KIPS |
|
Text Classification (Q)
|
93% |
3968
5.33 KIPS |
|
Machine Translation (SP)
|
100% |
4689
80.8 IPS |
|
Machine Translation (HP)
|
100% |
4536
78.1 IPS |
|
Machine Translation (Q)
|
98% |
4654
80.4 IPS |