Upload Date | July 11 2025 11:26 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 Max |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
Model | Mac Studio |
Model ID | Mac13,1 |
Motherboard | Mac13,1 |
CPU Information | |
---|---|
Name | Apple M1 Max |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M1 Max |
Base Frequency | 3.22 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4446
826.8 IPS |
|
Image Classification (HP)
|
100% |
4790
890.8 IPS |
|
Image Classification (Q)
|
96% |
4293
801.6 IPS |
|
Image Segmentation (SP)
|
100% |
10191
165.2 IPS |
|
Image Segmentation (HP)
|
100% |
10104
163.8 IPS |
|
Image Segmentation (Q)
|
99% |
9575
155.2 IPS |
|
Pose Estimation (SP)
|
100% |
47517
55.4 IPS |
|
Pose Estimation (HP)
|
100% |
50943
59.4 IPS |
|
Pose Estimation (Q)
|
96% |
49127
57.5 IPS |
|
Object Detection (SP)
|
100% |
4708
373.4 IPS |
|
Object Detection (HP)
|
100% |
5036
399.4 IPS |
|
Object Detection (Q)
|
92% |
4549
363.1 IPS |
|
Face Detection (SP)
|
100% |
18365
218.2 IPS |
|
Face Detection (HP)
|
100% |
19413
230.7 IPS |
|
Face Detection (Q)
|
100% |
15428
183.3 IPS |
|
Depth Estimation (SP)
|
100% |
23739
182.9 IPS |
|
Depth Estimation (HP)
|
99% |
24719
190.4 IPS |
|
Depth Estimation (Q)
|
86% |
22812
178.2 IPS |
|
Style Transfer (SP)
|
100% |
80063
102.9 IPS |
|
Style Transfer (HP)
|
100% |
96847
124.5 IPS |
|
Style Transfer (Q)
|
96% |
94544
122.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
15870
586.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
16691
616.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
14566
537.8 IPS |
|
Text Classification (SP)
|
100% |
2294
3.06 KIPS |
|
Text Classification (HP)
|
100% |
4035
5.39 KIPS |
|
Text Classification (Q)
|
93% |
4025
5.40 KIPS |
|
Machine Translation (SP)
|
100% |
1909
32.9 IPS |
|
Machine Translation (HP)
|
100% |
1883
32.4 IPS |
|
Machine Translation (Q)
|
98% |
1872
32.3 IPS |