User | nithinmohantk |
Upload Date | April 03 2025 10:39 AM |
Views | 4 |
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 | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
10147
1.89 KIPS |
|
Image Classification (HP)
|
100% |
10232
1.90 KIPS |
|
Image Classification (Q)
|
97% |
8809
1.64 KIPS |
|
Image Segmentation (SP)
|
100% |
19735
319.9 IPS |
|
Image Segmentation (HP)
|
100% |
20623
334.3 IPS |
|
Image Segmentation (Q)
|
99% |
21199
343.6 IPS |
|
Pose Estimation (SP)
|
100% |
107078
124.9 IPS |
|
Pose Estimation (HP)
|
100% |
109585
127.9 IPS |
|
Pose Estimation (Q)
|
95% |
104050
122.0 IPS |
|
Object Detection (SP)
|
100% |
9004
714.2 IPS |
|
Object Detection (HP)
|
100% |
9905
785.7 IPS |
|
Object Detection (Q)
|
91% |
8579
685.6 IPS |
|
Face Detection (SP)
|
100% |
39639
471.0 IPS |
|
Face Detection (HP)
|
100% |
41110
488.5 IPS |
|
Face Detection (Q)
|
100% |
32280
383.6 IPS |
|
Depth Estimation (SP)
|
100% |
44055
339.4 IPS |
|
Depth Estimation (HP)
|
99% |
47048
362.5 IPS |
|
Depth Estimation (Q)
|
85% |
41042
320.8 IPS |
|
Style Transfer (SP)
|
100% |
220792
283.8 IPS |
|
Style Transfer (HP)
|
100% |
241143
310.0 IPS |
|
Style Transfer (Q)
|
96% |
220070
284.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
29829
1.10 KIPS |
|
Image Super-Resolution (HP)
|
100% |
32538
1.20 KIPS |
|
Image Super-Resolution (Q)
|
99% |
26263
969.8 IPS |
|
Text Classification (SP)
|
100% |
2976
3.97 KIPS |
|
Text Classification (HP)
|
100% |
5438
7.26 KIPS |
|
Text Classification (Q)
|
93% |
5371
7.21 KIPS |
|
Machine Translation (SP)
|
100% |
3689
63.5 IPS |
|
Machine Translation (HP)
|
100% |
3626
62.5 IPS |
|
Machine Translation (Q)
|
98% |
3308
57.2 IPS |