User | Toda |
Upload Date | September 08 2025 10:58 AM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.6.1 (Build 24G90) |
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 | 3.30 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 192.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1346
250.2 IPS |
|
Image Classification (HP)
|
100% |
12367
2.30 KIPS |
|
Image Classification (Q)
|
96% |
15108
2.82 KIPS |
|
Image Segmentation (SP)
|
100% |
1618
26.2 IPS |
|
Image Segmentation (HP)
|
100% |
19185
311.0 IPS |
|
Image Segmentation (Q)
|
99% |
23776
385.4 IPS |
|
Pose Estimation (SP)
|
100% |
16052
18.7 IPS |
|
Pose Estimation (HP)
|
100% |
98664
115.1 IPS |
|
Pose Estimation (Q)
|
95% |
99919
117.1 IPS |
|
Object Detection (SP)
|
100% |
1688
133.9 IPS |
|
Object Detection (HP)
|
99% |
14923
1.19 KIPS |
|
Object Detection (Q)
|
91% |
16510
1.32 KIPS |
|
Face Detection (SP)
|
100% |
3510
41.7 IPS |
|
Face Detection (HP)
|
100% |
31358
372.6 IPS |
|
Face Detection (Q)
|
100% |
39058
464.1 IPS |
|
Depth Estimation (SP)
|
100% |
5437
41.9 IPS |
|
Depth Estimation (HP)
|
99% |
86247
664.5 IPS |
|
Depth Estimation (Q)
|
85% |
108020
844.1 IPS |
|
Style Transfer (SP)
|
100% |
26929
34.6 IPS |
|
Style Transfer (HP)
|
100% |
188757
242.6 IPS |
|
Style Transfer (Q)
|
96% |
193328
249.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5123
189.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
41426
1.53 KIPS |
|
Image Super-Resolution (Q)
|
99% |
46623
1.72 KIPS |
|
Text Classification (SP)
|
100% |
2199
2.93 KIPS |
|
Text Classification (HP)
|
100% |
3815
5.09 KIPS |
|
Text Classification (Q)
|
93% |
3835
5.15 KIPS |
|
Machine Translation (SP)
|
100% |
4154
71.6 IPS |
|
Machine Translation (HP)
|
100% |
3076
53.0 IPS |
|
Machine Translation (Q)
|
98% |
3226
55.8 IPS |