User | trode |
Upload Date | August 15 2024 05:15 PM |
Views | 5 |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | Mac Studio |
Model ID | Mac13,2 |
Motherboard | Mac13,2 |
CPU Information | |
---|---|
Name | Apple M1 Ultra |
Topology | 1 Processor, 20 Cores |
Identifier | Apple M1 Ultra |
Base Frequency | 3.21 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 4 Cores |
L1 Instruction Cache | 128 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 4.00 MB x 1 |
Memory Information | |
---|---|
Size | 128.00 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
773
144.6 IPS |
|
Image Classification (F16)
|
100% |
6474
1.21 KIPS |
|
Image Classification (I8)
|
99% |
6830
1.28 KIPS |
|
Image Segmentation (F32)
|
100% |
1462
24.4 IPS |
|
Image Segmentation (F16)
|
100% |
939
15.7 IPS |
|
Image Segmentation (I8)
|
100% |
928
15.5 IPS |
|
Pose Estimation (F32)
|
100% |
70171
85.0 IPS |
|
Pose Estimation (F16)
|
100% |
60871
73.7 IPS |
|
Pose Estimation (I8)
|
100% |
60223
72.9 IPS |
|
Object Detection (F32)
|
100% |
2188
163.3 IPS |
|
Object Detection (F16)
|
100% |
4367
326.0 IPS |
|
Object Detection (I8)
|
97% |
2128
158.9 IPS |
|
Face Detection (F32)
|
100% |
14916
177.4 IPS |
|
Face Detection (F16)
|
97% |
10294
122.4 IPS |
|
Face Detection (I8)
|
96% |
10370
123.3 IPS |
|
Depth Estimation (F32)
|
100% |
21879
169.7 IPS |
|
Depth Estimation (F16)
|
100% |
27970
216.9 IPS |
|
Depth Estimation (I8)
|
37% |
25767
199.8 IPS |
|
Style Transfer (F32)
|
100% |
104377
137.3 IPS |
|
Style Transfer (F16)
|
100% |
108110
142.2 IPS |
|
Style Transfer (I8)
|
100% |
113449
149.2 IPS |
|
Image Super-Resolution (F32)
|
100% |
9338
333.5 IPS |
|
Image Super-Resolution (F16)
|
100% |
14773
527.6 IPS |
|
Image Super-Resolution (I8)
|
100% |
14736
526.3 IPS |
|
Text Classification (F32)
|
100% |
722
1.04 KIPS |
|
Text Classification (F16)
|
100% |
406
583.5 IPS |
|
Text Classification (I8)
|
96% |
509
730.9 IPS |
|
Machine Translation (F32)
|
100% |
809
14.9 IPS |
|
Machine Translation (F16)
|
99% |
901
16.6 IPS |
|
Machine Translation (I8)
|
99% |
666
12.3 IPS |