User | nicknick1 |
Upload Date | January 07 2025 05:36 PM |
Views | 10 |
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, 14 Cores |
Identifier | Apple M4 Max |
Base Frequency | 4.50 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
9080
1.69 KIPS |
|
Image Classification (HP)
|
100% |
9560
1.78 KIPS |
|
Image Classification (Q)
|
97% |
8151
1.52 KIPS |
|
Image Segmentation (SP)
|
100% |
17247
279.6 IPS |
|
Image Segmentation (HP)
|
100% |
17799
288.5 IPS |
|
Image Segmentation (Q)
|
99% |
18357
297.6 IPS |
|
Pose Estimation (SP)
|
100% |
80442
93.9 IPS |
|
Pose Estimation (HP)
|
100% |
83497
97.4 IPS |
|
Pose Estimation (Q)
|
95% |
78709
92.3 IPS |
|
Object Detection (SP)
|
100% |
8971
711.6 IPS |
|
Object Detection (HP)
|
100% |
9457
750.1 IPS |
|
Object Detection (Q)
|
91% |
8169
652.8 IPS |
|
Face Detection (SP)
|
100% |
34431
409.1 IPS |
|
Face Detection (HP)
|
100% |
37055
440.3 IPS |
|
Face Detection (Q)
|
100% |
28424
337.7 IPS |
|
Depth Estimation (SP)
|
100% |
41999
323.6 IPS |
|
Depth Estimation (HP)
|
99% |
43858
337.9 IPS |
|
Depth Estimation (Q)
|
85% |
37083
289.8 IPS |
|
Style Transfer (SP)
|
100% |
189219
243.2 IPS |
|
Style Transfer (HP)
|
100% |
202730
260.6 IPS |
|
Style Transfer (Q)
|
96% |
189618
244.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
26143
965.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
27227
1.01 KIPS |
|
Image Super-Resolution (Q)
|
99% |
21986
811.8 IPS |
|
Text Classification (SP)
|
100% |
2953
3.94 KIPS |
|
Text Classification (HP)
|
100% |
5310
7.09 KIPS |
|
Text Classification (Q)
|
93% |
5293
7.10 KIPS |
|
Machine Translation (SP)
|
100% |
3254
56.1 IPS |
|
Machine Translation (HP)
|
100% |
3321
57.2 IPS |
|
Machine Translation (Q)
|
98% |
3333
57.6 IPS |