User | mstephan |
Upload Date | February 13 2025 06:44 AM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.3 (Build 24D60) |
Model | MacBook Pro (14-inch, 2024) |
Model ID | Mac16,8 |
Motherboard | Mac16,8 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.51 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
6829
1.27 KIPS |
|
Image Classification (HP)
|
100% |
7331
1.36 KIPS |
|
Image Classification (Q)
|
97% |
6234
1.16 KIPS |
|
Image Segmentation (SP)
|
100% |
10699
173.4 IPS |
|
Image Segmentation (HP)
|
100% |
11112
180.1 IPS |
|
Image Segmentation (Q)
|
99% |
11303
183.2 IPS |
|
Pose Estimation (SP)
|
100% |
46270
54.0 IPS |
|
Pose Estimation (HP)
|
100% |
48258
56.3 IPS |
|
Pose Estimation (Q)
|
95% |
45693
53.6 IPS |
|
Object Detection (SP)
|
100% |
6778
537.6 IPS |
|
Object Detection (HP)
|
100% |
7275
577.0 IPS |
|
Object Detection (Q)
|
91% |
6020
481.1 IPS |
|
Face Detection (SP)
|
100% |
23317
277.1 IPS |
|
Face Detection (HP)
|
100% |
24935
296.3 IPS |
|
Face Detection (Q)
|
100% |
18500
219.8 IPS |
|
Depth Estimation (SP)
|
100% |
31004
238.9 IPS |
|
Depth Estimation (HP)
|
99% |
32905
253.5 IPS |
|
Depth Estimation (Q)
|
85% |
27215
212.7 IPS |
|
Style Transfer (SP)
|
100% |
104863
134.8 IPS |
|
Style Transfer (HP)
|
100% |
112822
145.0 IPS |
|
Style Transfer (Q)
|
96% |
107058
138.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
16666
615.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
17218
635.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
13961
515.5 IPS |
|
Text Classification (SP)
|
100% |
2925
3.90 KIPS |
|
Text Classification (HP)
|
100% |
5159
6.89 KIPS |
|
Text Classification (Q)
|
93% |
5301
7.12 KIPS |
|
Machine Translation (SP)
|
100% |
2613
45.0 IPS |
|
Machine Translation (HP)
|
100% |
2735
47.1 IPS |
|
Machine Translation (Q)
|
98% |
2622
45.3 IPS |