User | petergraening |
Upload Date | January 17 2025 04:40 AM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
Model | MacBook Pro (16-inch, 2024) |
Model ID | Mac16,5 |
Motherboard | Mac16,5 |
CPU Information | |
---|---|
Name | Apple M4 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M4 Max |
Base Frequency | 4.51 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
9945
1.85 KIPS |
|
Image Classification (HP)
|
100% |
10572
1.97 KIPS |
|
Image Classification (Q)
|
97% |
8741
1.63 KIPS |
|
Image Segmentation (SP)
|
100% |
19510
316.3 IPS |
|
Image Segmentation (HP)
|
100% |
20611
334.1 IPS |
|
Image Segmentation (Q)
|
99% |
21060
341.4 IPS |
|
Pose Estimation (SP)
|
100% |
106474
124.2 IPS |
|
Pose Estimation (HP)
|
100% |
109933
128.3 IPS |
|
Pose Estimation (Q)
|
95% |
104107
122.0 IPS |
|
Object Detection (SP)
|
100% |
8707
690.7 IPS |
|
Object Detection (HP)
|
100% |
9706
769.9 IPS |
|
Object Detection (Q)
|
91% |
8301
663.3 IPS |
|
Face Detection (SP)
|
100% |
39073
464.3 IPS |
|
Face Detection (HP)
|
100% |
38975
463.1 IPS |
|
Face Detection (Q)
|
100% |
31140
370.0 IPS |
|
Depth Estimation (SP)
|
100% |
43658
336.4 IPS |
|
Depth Estimation (HP)
|
99% |
46100
355.2 IPS |
|
Depth Estimation (Q)
|
85% |
39221
306.5 IPS |
|
Style Transfer (SP)
|
100% |
221445
284.7 IPS |
|
Style Transfer (HP)
|
100% |
239288
307.6 IPS |
|
Style Transfer (Q)
|
96% |
220282
284.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
30424
1.12 KIPS |
|
Image Super-Resolution (HP)
|
100% |
32381
1.20 KIPS |
|
Image Super-Resolution (Q)
|
99% |
26088
963.3 IPS |
|
Text Classification (SP)
|
100% |
2974
3.97 KIPS |
|
Text Classification (HP)
|
100% |
5422
7.24 KIPS |
|
Text Classification (Q)
|
93% |
5528
7.42 KIPS |
|
Machine Translation (SP)
|
100% |
3483
60.0 IPS |
|
Machine Translation (HP)
|
100% |
2682
46.2 IPS |
|
Machine Translation (Q)
|
98% |
3578
61.8 IPS |