User | davidofun |
Upload Date | September 01 2025 11:48 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 |
System Information | |
---|---|
Operating System | macOS 26.0 (Build 25A5349a) |
Model | Mac15,12 |
Model ID | Mac15,12 |
Motherboard | Mac15,12 |
CPU Information | |
---|---|
Name | Apple M3 |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M3 |
Base Frequency | 4.01 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4242
788.9 IPS |
|
Image Classification (HP)
|
100% |
4636
862.1 IPS |
|
Image Classification (Q)
|
96% |
4147
774.4 IPS |
|
Image Segmentation (SP)
|
100% |
6332
102.7 IPS |
|
Image Segmentation (HP)
|
100% |
7004
113.5 IPS |
|
Image Segmentation (Q)
|
99% |
6720
108.9 IPS |
|
Pose Estimation (SP)
|
100% |
23439
27.3 IPS |
|
Pose Estimation (HP)
|
100% |
26609
31.0 IPS |
|
Pose Estimation (Q)
|
96% |
25940
30.4 IPS |
|
Object Detection (SP)
|
100% |
4264
338.2 IPS |
|
Object Detection (HP)
|
100% |
4760
377.6 IPS |
|
Object Detection (Q)
|
92% |
4419
352.7 IPS |
|
Face Detection (SP)
|
100% |
11271
133.9 IPS |
|
Face Detection (HP)
|
100% |
15177
180.3 IPS |
|
Face Detection (Q)
|
100% |
12204
145.0 IPS |
|
Depth Estimation (SP)
|
100% |
18123
139.6 IPS |
|
Depth Estimation (HP)
|
99% |
20370
156.9 IPS |
|
Depth Estimation (Q)
|
86% |
18504
144.5 IPS |
|
Style Transfer (SP)
|
100% |
50060
64.4 IPS |
|
Style Transfer (HP)
|
100% |
59569
76.6 IPS |
|
Style Transfer (Q)
|
96% |
58150
75.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
10465
386.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
10703
395.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
9322
344.2 IPS |
|
Text Classification (SP)
|
100% |
3126
4.17 KIPS |
|
Text Classification (HP)
|
99% |
5171
6.90 KIPS |
|
Text Classification (Q)
|
93% |
5160
6.92 KIPS |
|
Machine Translation (SP)
|
100% |
4332
74.6 IPS |
|
Machine Translation (HP)
|
100% |
4649
80.1 IPS |
|
Machine Translation (Q)
|
98% |
4617
79.8 IPS |