User | f180n4cc1 |
Upload Date | January 02 2025 09:24 AM |
Views | 18 |
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 | 4.50 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
10227
1.90 KIPS |
|
Image Classification (HP)
|
100% |
10356
1.93 KIPS |
|
Image Classification (Q)
|
97% |
8724
1.63 KIPS |
|
Image Segmentation (SP)
|
100% |
19557
317.0 IPS |
|
Image Segmentation (HP)
|
100% |
20349
329.9 IPS |
|
Image Segmentation (Q)
|
99% |
21069
341.5 IPS |
|
Pose Estimation (SP)
|
100% |
107316
125.2 IPS |
|
Pose Estimation (HP)
|
100% |
110321
128.7 IPS |
|
Pose Estimation (Q)
|
95% |
103828
121.7 IPS |
|
Object Detection (SP)
|
100% |
9122
723.6 IPS |
|
Object Detection (HP)
|
100% |
10146
804.8 IPS |
|
Object Detection (Q)
|
91% |
8683
693.8 IPS |
|
Face Detection (SP)
|
100% |
39978
475.0 IPS |
|
Face Detection (HP)
|
100% |
41052
487.8 IPS |
|
Face Detection (Q)
|
100% |
32858
390.4 IPS |
|
Depth Estimation (SP)
|
100% |
44914
346.0 IPS |
|
Depth Estimation (HP)
|
99% |
47096
362.9 IPS |
|
Depth Estimation (Q)
|
85% |
41159
321.7 IPS |
|
Style Transfer (SP)
|
100% |
222411
285.9 IPS |
|
Style Transfer (HP)
|
100% |
240238
308.8 IPS |
|
Style Transfer (Q)
|
96% |
218522
282.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
30219
1.12 KIPS |
|
Image Super-Resolution (HP)
|
100% |
33209
1.23 KIPS |
|
Image Super-Resolution (Q)
|
99% |
27671
1.02 KIPS |
|
Text Classification (SP)
|
100% |
2986
3.99 KIPS |
|
Text Classification (HP)
|
100% |
5427
7.24 KIPS |
|
Text Classification (Q)
|
93% |
5399
7.25 KIPS |
|
Machine Translation (SP)
|
100% |
3658
63.0 IPS |
|
Machine Translation (HP)
|
100% |
3411
58.8 IPS |
|
Machine Translation (Q)
|
98% |
3395
58.7 IPS |