User | khodaparastan |
Upload Date | May 06 2025 02:24 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.4.1 (Build 24E263) |
Model | MacBook Pro (14-inch, 2023) |
Model ID | Mac14,5 |
Motherboard | Mac14,5 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.48 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 96.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
6727
1.25 KIPS |
|
Image Classification (HP)
|
100% |
6963
1.29 KIPS |
|
Image Classification (Q)
|
96% |
6494
1.21 KIPS |
|
Image Segmentation (SP)
|
100% |
13798
223.7 IPS |
|
Image Segmentation (HP)
|
100% |
13928
225.8 IPS |
|
Image Segmentation (Q)
|
99% |
13102
212.4 IPS |
|
Pose Estimation (SP)
|
100% |
82548
96.3 IPS |
|
Pose Estimation (HP)
|
100% |
86938
101.4 IPS |
|
Pose Estimation (Q)
|
96% |
83407
97.7 IPS |
|
Object Detection (SP)
|
100% |
6377
505.8 IPS |
|
Object Detection (HP)
|
100% |
6779
537.7 IPS |
|
Object Detection (Q)
|
92% |
6216
496.2 IPS |
|
Face Detection (SP)
|
100% |
27545
327.3 IPS |
|
Face Detection (HP)
|
100% |
28858
342.9 IPS |
|
Face Detection (Q)
|
100% |
24316
288.9 IPS |
|
Depth Estimation (SP)
|
100% |
32919
253.6 IPS |
|
Depth Estimation (HP)
|
99% |
34187
263.4 IPS |
|
Depth Estimation (Q)
|
85% |
31217
244.1 IPS |
|
Style Transfer (SP)
|
100% |
136205
175.1 IPS |
|
Style Transfer (HP)
|
100% |
152861
196.5 IPS |
|
Style Transfer (Q)
|
96% |
148780
192.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
20376
752.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
20279
748.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
18167
670.8 IPS |
|
Text Classification (SP)
|
100% |
2349
3.14 KIPS |
|
Text Classification (HP)
|
100% |
4165
5.56 KIPS |
|
Text Classification (Q)
|
93% |
4103
5.51 KIPS |
|
Machine Translation (SP)
|
100% |
1793
30.9 IPS |
|
Machine Translation (HP)
|
100% |
1831
31.5 IPS |
|
Machine Translation (Q)
|
98% |
1821
31.5 IPS |