User | machinecoach |
Upload Date | December 09 2024 08:09 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2082) |
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 | 4.50 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
8159
1.52 KIPS |
|
Image Classification (HP)
|
100% |
8902
1.66 KIPS |
|
Image Classification (Q)
|
97% |
7125
1.33 KIPS |
|
Image Segmentation (SP)
|
100% |
12334
199.9 IPS |
|
Image Segmentation (HP)
|
100% |
13230
214.5 IPS |
|
Image Segmentation (Q)
|
99% |
13500
218.8 IPS |
|
Pose Estimation (SP)
|
100% |
56854
66.3 IPS |
|
Pose Estimation (HP)
|
100% |
59347
69.2 IPS |
|
Pose Estimation (Q)
|
95% |
56252
65.9 IPS |
|
Object Detection (SP)
|
100% |
7320
580.6 IPS |
|
Object Detection (HP)
|
100% |
7885
625.5 IPS |
|
Object Detection (Q)
|
91% |
6645
531.0 IPS |
|
Face Detection (SP)
|
100% |
25699
305.4 IPS |
|
Face Detection (HP)
|
100% |
29202
347.0 IPS |
|
Face Detection (Q)
|
100% |
20835
247.6 IPS |
|
Depth Estimation (SP)
|
100% |
34055
262.4 IPS |
|
Depth Estimation (HP)
|
99% |
36027
277.6 IPS |
|
Depth Estimation (Q)
|
85% |
29498
230.5 IPS |
|
Style Transfer (SP)
|
100% |
124705
160.3 IPS |
|
Style Transfer (HP)
|
100% |
136625
175.6 IPS |
|
Style Transfer (Q)
|
96% |
127594
164.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
23544
869.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
24387
900.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
20460
755.5 IPS |
|
Text Classification (SP)
|
100% |
2960
3.95 KIPS |
|
Text Classification (HP)
|
100% |
5241
7.00 KIPS |
|
Text Classification (Q)
|
93% |
5194
6.97 KIPS |
|
Machine Translation (SP)
|
100% |
2707
46.6 IPS |
|
Machine Translation (HP)
|
100% |
2988
51.5 IPS |
|
Machine Translation (Q)
|
98% |
2723
47.1 IPS |