User | DFW |
Upload Date | September 16 2025 05:16 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.7 (Build 24G222) |
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 | 192.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1447
269.2 IPS |
|
Image Classification (HP)
|
100% |
13831
2.57 KIPS |
|
Image Classification (Q)
|
96% |
16054
3.00 KIPS |
|
Image Segmentation (SP)
|
100% |
1685
27.3 IPS |
|
Image Segmentation (HP)
|
100% |
19378
314.1 IPS |
|
Image Segmentation (Q)
|
99% |
24465
396.6 IPS |
|
Pose Estimation (SP)
|
100% |
18250
21.3 IPS |
|
Pose Estimation (HP)
|
100% |
106416
124.2 IPS |
|
Pose Estimation (Q)
|
95% |
105904
124.1 IPS |
|
Object Detection (SP)
|
100% |
1791
142.0 IPS |
|
Object Detection (HP)
|
99% |
16196
1.29 KIPS |
|
Object Detection (Q)
|
91% |
18334
1.46 KIPS |
|
Face Detection (SP)
|
100% |
3724
44.3 IPS |
|
Face Detection (HP)
|
100% |
32816
389.9 IPS |
|
Face Detection (Q)
|
100% |
45239
537.5 IPS |
|
Depth Estimation (SP)
|
100% |
6236
48.0 IPS |
|
Depth Estimation (HP)
|
99% |
88466
681.6 IPS |
|
Depth Estimation (Q)
|
85% |
110391
862.7 IPS |
|
Style Transfer (SP)
|
100% |
29313
37.7 IPS |
|
Style Transfer (HP)
|
100% |
206844
265.9 IPS |
|
Style Transfer (Q)
|
96% |
194592
251.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
5786
213.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
41749
1.54 KIPS |
|
Image Super-Resolution (Q)
|
99% |
49985
1.85 KIPS |
|
Text Classification (SP)
|
100% |
2318
3.09 KIPS |
|
Text Classification (HP)
|
100% |
4115
5.49 KIPS |
|
Text Classification (Q)
|
93% |
4089
5.49 KIPS |
|
Machine Translation (SP)
|
100% |
4455
76.7 IPS |
|
Machine Translation (HP)
|
100% |
4118
70.9 IPS |
|
Machine Translation (Q)
|
98% |
4367
75.5 IPS |