User | f180n4cc1 |
Upload Date | January 02 2025 09:25 AM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
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 | 4.50 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2128
395.8 IPS |
|
Image Classification (HP)
|
100% |
17575
3.27 KIPS |
|
Image Classification (Q)
|
97% |
23329
4.35 KIPS |
|
Image Segmentation (SP)
|
100% |
2615
42.4 IPS |
|
Image Segmentation (HP)
|
100% |
22489
364.6 IPS |
|
Image Segmentation (Q)
|
99% |
31091
504.0 IPS |
|
Pose Estimation (SP)
|
100% |
19241
22.5 IPS |
|
Pose Estimation (HP)
|
100% |
122713
143.2 IPS |
|
Pose Estimation (Q)
|
95% |
230153
269.8 IPS |
|
Object Detection (SP)
|
100% |
2597
206.0 IPS |
|
Object Detection (HP)
|
100% |
19369
1.54 KIPS |
|
Object Detection (Q)
|
91% |
23631
1.89 KIPS |
|
Face Detection (SP)
|
100% |
4838
57.5 IPS |
|
Face Detection (HP)
|
100% |
44786
532.1 IPS |
|
Face Detection (Q)
|
100% |
54861
651.9 IPS |
|
Depth Estimation (SP)
|
100% |
9172
70.7 IPS |
|
Depth Estimation (HP)
|
99% |
105167
810.2 IPS |
|
Depth Estimation (Q)
|
85% |
176921
1.38 KIPS |
|
Style Transfer (SP)
|
100% |
37397
48.1 IPS |
|
Style Transfer (HP)
|
100% |
230753
296.6 IPS |
|
Style Transfer (Q)
|
96% |
296591
382.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
7255
267.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
46170
1.70 KIPS |
|
Image Super-Resolution (Q)
|
99% |
77330
2.86 KIPS |
|
Text Classification (SP)
|
100% |
2976
3.97 KIPS |
|
Text Classification (HP)
|
100% |
5590
7.46 KIPS |
|
Text Classification (Q)
|
93% |
5732
7.69 KIPS |
|
Machine Translation (SP)
|
100% |
6135
105.7 IPS |
|
Machine Translation (HP)
|
100% |
16514
284.5 IPS |
|
Machine Translation (Q)
|
98% |
16568
286.3 IPS |