User | Gonfonix |
Upload Date | November 10 2024 02:08 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
Model | Mac Pro (2023) |
Model ID | Mac14,8 |
Motherboard | Mac14,8 |
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% |
1467
272.8 IPS |
|
Image Classification (HP)
|
100% |
13467
2.50 KIPS |
|
Image Classification (Q)
|
96% |
15517
2.90 KIPS |
|
Image Segmentation (SP)
|
100% |
1801
29.2 IPS |
|
Image Segmentation (HP)
|
100% |
19337
313.5 IPS |
|
Image Segmentation (Q)
|
99% |
24565
398.2 IPS |
|
Pose Estimation (SP)
|
100% |
18554
21.6 IPS |
|
Pose Estimation (HP)
|
100% |
105230
122.8 IPS |
|
Pose Estimation (Q)
|
95% |
103839
121.7 IPS |
|
Object Detection (SP)
|
100% |
1855
147.1 IPS |
|
Object Detection (HP)
|
99% |
15822
1.26 KIPS |
|
Object Detection (Q)
|
91% |
17499
1.40 KIPS |
|
Face Detection (SP)
|
100% |
3703
44.0 IPS |
|
Face Detection (HP)
|
100% |
35639
423.5 IPS |
|
Face Detection (Q)
|
100% |
45856
544.9 IPS |
|
Depth Estimation (SP)
|
100% |
6344
48.9 IPS |
|
Depth Estimation (HP)
|
99% |
85303
657.2 IPS |
|
Depth Estimation (Q)
|
85% |
106067
828.9 IPS |
|
Style Transfer (SP)
|
100% |
27841
35.8 IPS |
|
Style Transfer (HP)
|
100% |
204340
262.7 IPS |
|
Style Transfer (Q)
|
96% |
186733
241.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5991
221.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
40086
1.48 KIPS |
|
Image Super-Resolution (Q)
|
99% |
47737
1.76 KIPS |
|
Text Classification (SP)
|
100% |
2351
3.14 KIPS |
|
Text Classification (HP)
|
100% |
4087
5.46 KIPS |
|
Text Classification (Q)
|
93% |
4031
5.41 KIPS |
|
Machine Translation (SP)
|
100% |
4963
85.5 IPS |
|
Machine Translation (HP)
|
100% |
3683
63.4 IPS |
|
Machine Translation (Q)
|
98% |
4506
77.9 IPS |