User | gigaouch |
Upload Date | June 06 2025 03:37 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
Model | MacBook Pro (14-inch, Nov 2023) |
Model ID | Mac15,8 |
Motherboard | Mac15,8 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M3 Max |
Base Frequency | 4.02 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
8164
1.52 KIPS |
|
Image Classification (HP)
|
100% |
8642
1.61 KIPS |
|
Image Classification (Q)
|
96% |
7906
1.48 KIPS |
|
Image Segmentation (SP)
|
100% |
19822
321.3 IPS |
|
Image Segmentation (HP)
|
100% |
20655
334.8 IPS |
|
Image Segmentation (Q)
|
99% |
19651
318.6 IPS |
|
Pose Estimation (SP)
|
100% |
91954
107.3 IPS |
|
Pose Estimation (HP)
|
100% |
95776
111.8 IPS |
|
Pose Estimation (Q)
|
96% |
91884
107.6 IPS |
|
Object Detection (SP)
|
100% |
7820
620.3 IPS |
|
Object Detection (HP)
|
100% |
8528
676.4 IPS |
|
Object Detection (Q)
|
92% |
7741
617.9 IPS |
|
Face Detection (SP)
|
100% |
31511
374.4 IPS |
|
Face Detection (HP)
|
100% |
35749
424.8 IPS |
|
Face Detection (Q)
|
100% |
30999
368.3 IPS |
|
Depth Estimation (SP)
|
100% |
38365
295.6 IPS |
|
Depth Estimation (HP)
|
99% |
40422
311.4 IPS |
|
Depth Estimation (Q)
|
86% |
37289
291.3 IPS |
|
Style Transfer (SP)
|
100% |
188965
242.9 IPS |
|
Style Transfer (HP)
|
100% |
204124
262.4 IPS |
|
Style Transfer (Q)
|
96% |
195919
252.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
25411
938.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
26048
961.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
23811
879.2 IPS |
|
Text Classification (SP)
|
100% |
3147
4.20 KIPS |
|
Text Classification (HP)
|
100% |
5493
7.33 KIPS |
|
Text Classification (Q)
|
93% |
5026
6.75 KIPS |
|
Machine Translation (SP)
|
100% |
2490
42.9 IPS |
|
Machine Translation (HP)
|
100% |
2856
49.2 IPS |
|
Machine Translation (Q)
|
98% |
2291
39.6 IPS |