User | tebruno99 |
Upload Date | March 27 2025 11:20 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.3.1 (Build 24D70) |
Model | MacBook Pro (16-inch, 2024) |
Model ID | Mac16,7 |
Motherboard | Mac16,7 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.51 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7905
1.47 KIPS |
|
Image Classification (HP)
|
100% |
8574
1.59 KIPS |
|
Image Classification (Q)
|
97% |
7144
1.33 KIPS |
|
Image Segmentation (SP)
|
100% |
12270
198.9 IPS |
|
Image Segmentation (HP)
|
100% |
13383
217.0 IPS |
|
Image Segmentation (Q)
|
99% |
13466
218.3 IPS |
|
Pose Estimation (SP)
|
100% |
56895
66.4 IPS |
|
Pose Estimation (HP)
|
100% |
59339
69.2 IPS |
|
Pose Estimation (Q)
|
95% |
56160
65.8 IPS |
|
Object Detection (SP)
|
100% |
7345
582.6 IPS |
|
Object Detection (HP)
|
100% |
7836
621.6 IPS |
|
Object Detection (Q)
|
91% |
6523
521.2 IPS |
|
Face Detection (SP)
|
100% |
25903
307.8 IPS |
|
Face Detection (HP)
|
100% |
27933
331.9 IPS |
|
Face Detection (Q)
|
100% |
21650
257.3 IPS |
|
Depth Estimation (SP)
|
100% |
33865
260.9 IPS |
|
Depth Estimation (HP)
|
99% |
36635
282.3 IPS |
|
Depth Estimation (Q)
|
85% |
30350
237.2 IPS |
|
Style Transfer (SP)
|
100% |
124049
159.5 IPS |
|
Style Transfer (HP)
|
100% |
135674
174.4 IPS |
|
Style Transfer (Q)
|
96% |
128484
165.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
23259
858.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
25162
929.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
20145
743.8 IPS |
|
Text Classification (SP)
|
100% |
2960
3.95 KIPS |
|
Text Classification (HP)
|
100% |
5369
7.17 KIPS |
|
Text Classification (Q)
|
93% |
5309
7.13 KIPS |
|
Machine Translation (SP)
|
100% |
1470
25.3 IPS |
|
Machine Translation (HP)
|
100% |
1514
26.1 IPS |
|
Machine Translation (Q)
|
98% |
1497
25.9 IPS |