User | mbeauchesne |
Upload Date | March 01 2025 07:49 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
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 | 3.27 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1448
269.2 IPS |
|
Image Classification (HP)
|
100% |
13345
2.48 KIPS |
|
Image Classification (Q)
|
96% |
16683
3.12 KIPS |
|
Image Segmentation (SP)
|
100% |
1758
28.5 IPS |
|
Image Segmentation (HP)
|
100% |
19474
315.7 IPS |
|
Image Segmentation (Q)
|
99% |
23675
383.8 IPS |
|
Pose Estimation (SP)
|
100% |
16994
19.8 IPS |
|
Pose Estimation (HP)
|
100% |
106684
124.5 IPS |
|
Pose Estimation (Q)
|
95% |
106100
124.4 IPS |
|
Object Detection (SP)
|
100% |
1815
144.0 IPS |
|
Object Detection (HP)
|
99% |
16076
1.28 KIPS |
|
Object Detection (Q)
|
91% |
17862
1.43 KIPS |
|
Face Detection (SP)
|
100% |
3742
44.5 IPS |
|
Face Detection (HP)
|
100% |
34690
412.2 IPS |
|
Face Detection (Q)
|
100% |
45071
535.5 IPS |
|
Depth Estimation (SP)
|
100% |
6398
49.3 IPS |
|
Depth Estimation (HP)
|
99% |
86536
666.7 IPS |
|
Depth Estimation (Q)
|
85% |
107358
839.0 IPS |
|
Style Transfer (SP)
|
100% |
28365
36.5 IPS |
|
Style Transfer (HP)
|
100% |
205985
264.8 IPS |
|
Style Transfer (Q)
|
96% |
193210
249.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5561
205.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
40751
1.50 KIPS |
|
Image Super-Resolution (Q)
|
99% |
49865
1.84 KIPS |
|
Text Classification (SP)
|
100% |
2262
3.02 KIPS |
|
Text Classification (HP)
|
100% |
3858
5.15 KIPS |
|
Text Classification (Q)
|
93% |
3901
5.24 KIPS |
|
Machine Translation (SP)
|
100% |
4933
85.0 IPS |
|
Machine Translation (HP)
|
100% |
3556
61.3 IPS |
|
Machine Translation (Q)
|
98% |
3641
62.9 IPS |