User | tphillips63 |
Upload Date | October 29 2024 08:49 PM |
Views | 5 |
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 | 3.67 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 192.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1464
272.3 IPS |
|
Image Classification (HP)
|
100% |
13195
2.45 KIPS |
|
Image Classification (Q)
|
96% |
15624
2.92 KIPS |
|
Image Segmentation (SP)
|
100% |
1818
29.5 IPS |
|
Image Segmentation (HP)
|
100% |
19405
314.6 IPS |
|
Image Segmentation (Q)
|
99% |
24468
396.6 IPS |
|
Pose Estimation (SP)
|
100% |
18756
21.9 IPS |
|
Pose Estimation (HP)
|
100% |
104971
122.5 IPS |
|
Pose Estimation (Q)
|
95% |
104138
122.1 IPS |
|
Object Detection (SP)
|
100% |
1855
147.1 IPS |
|
Object Detection (HP)
|
99% |
15834
1.26 KIPS |
|
Object Detection (Q)
|
91% |
17552
1.40 KIPS |
|
Face Detection (SP)
|
100% |
3580
42.5 IPS |
|
Face Detection (HP)
|
100% |
35570
422.6 IPS |
|
Face Detection (Q)
|
100% |
45992
546.5 IPS |
|
Depth Estimation (SP)
|
100% |
6508
50.1 IPS |
|
Depth Estimation (HP)
|
99% |
86421
665.8 IPS |
|
Depth Estimation (Q)
|
85% |
106985
836.0 IPS |
|
Style Transfer (SP)
|
100% |
27489
35.3 IPS |
|
Style Transfer (HP)
|
100% |
202974
260.9 IPS |
|
Style Transfer (Q)
|
96% |
188294
243.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
6029
222.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
40047
1.48 KIPS |
|
Image Super-Resolution (Q)
|
99% |
47899
1.77 KIPS |
|
Text Classification (SP)
|
100% |
2354
3.14 KIPS |
|
Text Classification (HP)
|
100% |
4070
5.43 KIPS |
|
Text Classification (Q)
|
93% |
4065
5.46 KIPS |
|
Machine Translation (SP)
|
100% |
4964
85.5 IPS |
|
Machine Translation (HP)
|
100% |
3631
62.5 IPS |
|
Machine Translation (Q)
|
98% |
3852
66.6 IPS |