User | Aaronage |
Upload Date | May 01 2025 09:27 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
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 | 3.49 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
6238
1.16 KIPS |
|
Image Classification (HP)
|
100% |
6264
1.16 KIPS |
|
Image Classification (Q)
|
97% |
5532
1.03 KIPS |
|
Image Segmentation (SP)
|
100% |
16200
262.6 IPS |
|
Image Segmentation (HP)
|
100% |
16535
268.0 IPS |
|
Image Segmentation (Q)
|
99% |
16965
275.0 IPS |
|
Pose Estimation (SP)
|
100% |
106451
124.2 IPS |
|
Pose Estimation (HP)
|
100% |
111098
129.6 IPS |
|
Pose Estimation (Q)
|
95% |
102352
120.0 IPS |
|
Object Detection (SP)
|
100% |
6222
493.5 IPS |
|
Object Detection (HP)
|
100% |
6245
495.3 IPS |
|
Object Detection (Q)
|
91% |
5535
442.3 IPS |
|
Face Detection (SP)
|
100% |
32236
383.0 IPS |
|
Face Detection (HP)
|
100% |
32336
384.2 IPS |
|
Face Detection (Q)
|
100% |
25193
299.3 IPS |
|
Depth Estimation (SP)
|
100% |
33034
254.5 IPS |
|
Depth Estimation (HP)
|
99% |
34923
269.1 IPS |
|
Depth Estimation (Q)
|
85% |
30084
235.1 IPS |
|
Style Transfer (SP)
|
100% |
194944
250.6 IPS |
|
Style Transfer (HP)
|
100% |
200562
257.8 IPS |
|
Style Transfer (Q)
|
96% |
185956
240.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
24232
894.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
24633
909.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
20171
744.8 IPS |
|
Text Classification (SP)
|
100% |
2299
3.07 KIPS |
|
Text Classification (HP)
|
100% |
4044
5.40 KIPS |
|
Text Classification (Q)
|
93% |
4016
5.39 KIPS |
|
Machine Translation (SP)
|
100% |
2373
40.9 IPS |
|
Machine Translation (HP)
|
100% |
2314
39.9 IPS |
|
Machine Translation (Q)
|
98% |
2190
37.8 IPS |