Hugging Face's logo

EdgeFirst
/
yolov8-seg

Image Segmentation
LiteRT
ONNX
edgefirst
edge-ai
npu
int8
yolo
nxp
hailo
jetson
embedded
Eval Results (legacy)
Model card Files
xet
 Community
1
sebastientaylor commited on
Commit
d0e15a6
·
verified ·
1 Parent(s): e86fe7d

Update model card for yolov8-seg

Browse files
Files changed (1) hide show
  1. README.md +30 -24
README.md CHANGED
@@ -105,18 +105,20 @@ Row conventions in the table below:
105
  | Nano | Apple M2 Max — CoreML Neural Engine (FP16) | 49.88% | 28.46% | -0.68 | 2.74 | 10.21 | 422.9 | ~424 | [v-72c](https://edgefirst.studio/public/validation/v-72c/details?mode=charts) |
106
  | Nano | Apple M2 Max — CoreML Metal GPU (FP16) | 49.94% | 28.47% | -0.67 | 6.64 | 16.93 | 307.1 | ~307 | [v-736](https://edgefirst.studio/public/validation/v-736/details?mode=charts) |
107
  | Nano | Apple M2 Max — CoreML CPU (FP16) | 50.78% | 28.92% | -0.22 | 21.74 | 29.90 | 87.2 | ~87 | [v-9f4](https://edgefirst.studio/public/validation/v-9f4/details?mode=charts) |
108
- | Nano | Apple iPhone 17 Pro — CoreML Neural Engine (FP16) | 51.14% | 29.20% | +0.06 | — | — | 160.3 | ~429 | [v-c06](https://edgefirst.studio/public/validation/v-c06/details?mode=charts) |
109
- | Nano | Apple iPhone 17 Pro — CoreML Metal GPU (FP16) | 51.14% | 29.14% | +0.00 | — | — | 121.4 | ~136 | [v-c04](https://edgefirst.studio/public/validation/v-c04/details?mode=charts) |
110
- | Nano | Apple iPhone 17 Pro — CoreML CPU (FP16) | 51.15% | 29.16% | +0.02 | — | — | 64.8 | ~67 | [v-c03](https://edgefirst.studio/public/validation/v-c03/details?mode=charts) |
111
- | Nano | Apple iPhone 15 Pro — CoreML Neural Engine (FP16) | 51.13% | 29.19% | +0.05 | — | — | 117.8 | ~375 | [v-c0c](https://edgefirst.studio/public/validation/v-c0c/details?mode=charts) |
112
- | Nano | Apple iPhone 15 Pro — CoreML Metal GPU (FP16) | 51.14% | 29.15% | +0.01 | — | — | 73.3 | ~80 | [v-c0a](https://edgefirst.studio/public/validation/v-c0a/details?mode=charts) |
113
- | Nano | Apple iPhone 15 Pro — CoreML CPU (FP16) | 51.14% | 29.16% | +0.02 | — | — | 49.0 | ~51 | [v-c08](https://edgefirst.studio/public/validation/v-c08/details?mode=charts) |
114
  | Nano | NXP i.MX 8M Plus + VeriSilicon NPU (FRDM) | 48.83% | 27.59% | -1.55 | 79.61 | 199.44 | 10.6 | ~12 | [v-8d7](https://edgefirst.studio/public/validation/v-8d7/details?mode=charts) |
 
 
115
  | Nano | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — latency | 48.87% | 27.63% | -1.51 | 20.62 | 116.40 | 20.8 | ~13 | [v-8cf](https://edgefirst.studio/public/validation/v-8cf/details?mode=charts) |
116
  | Nano | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 38.09% | 21.84% | -7.30 ⚠ | 93.69 | 139.74 | 39.9 | ~40 | [v-8ce](https://edgefirst.studio/public/validation/v-8ce/details?mode=charts) |
117
  | Nano | NXP i.MX 95 + eIQ Neutron NPU (Phytec) — throughput | 48.87% | 27.63% | -1.51 | 24.83 | 166.24 | 23.7 | ~24 | [v-8a8](https://edgefirst.studio/public/validation/v-8a8/details?mode=charts) |
118
- | Nano | NXP i.MX 95 + eIQ Neutron NPU (Verdin) — latency | 38.58% | 22.11% | -7.03 ⚠ | 47.51 | 69.79 | 20.0 | ~20 | [v-bcf](https://edgefirst.studio/public/validation/v-bcf/details?mode=charts) |
119
- | Nano | NXP i.MX 95 + eIQ Neutron NPU (Verdin) — throughput | 49.62% | 27.97% | -1.17 | 20.89 | 152.13 | 21.4 | ~28 | [v-bce](https://edgefirst.studio/public/validation/v-bce/details?mode=charts) |
120
  | Nano | NXP Ara240 (FRDM) — latency | 47.22% | 26.62% | -2.52 | 9.63 | 42.97 | 50.4 | ~56 | [v-a18](https://edgefirst.studio/public/validation/v-a18/details?mode=charts) |
121
  | Nano | NXP Ara240 (FRDM) — throughput | 47.22% | 26.62% | -2.52 | 9.80 | 62.62 | 51.7 | ~226 | [v-a19](https://edgefirst.studio/public/validation/v-a19/details?mode=charts) |
122
  | Nano | Raspberry Pi 5 + Hailo-8L NPU | 49.28% | 28.02% | -1.12 | 16.18 | 38.25 | 53.7 | ~54 | [v-8e5](https://edgefirst.studio/public/validation/v-8e5/details?mode=charts) |
@@ -127,18 +129,20 @@ Row conventions in the table below:
127
  | Small | Apple M2 Max — CoreML Neural Engine (FP16) | 59.62% | 34.65% | -0.18 | 6.18 | 13.83 | 261.8 | ~262 | [v-9e9](https://edgefirst.studio/public/validation/v-9e9/details?mode=charts) |
128
  | Small | Apple M2 Max — CoreML Metal GPU (FP16) | 59.61% | 34.58% | -0.25 | 21.34 | 29.86 | 133.8 | ~134 | [v-9e8](https://edgefirst.studio/public/validation/v-9e8/details?mode=charts) |
129
  | Small | Apple M2 Max — CoreML CPU (FP16) | 59.57% | 34.54% | -0.29 | 41.25 | 49.04 | 47.0 | ~47 | [v-9e7](https://edgefirst.studio/public/validation/v-9e7/details?mode=charts) |
130
- | Small | Apple iPhone 17 Pro — CoreML Neural Engine (FP16) | 59.63% | 34.62% | -0.21 | — | — | 186.5 | ~199 | [v-c67](https://edgefirst.studio/public/validation/v-c67/details?mode=charts) |
131
- | Small | Apple iPhone 17 Pro — CoreML Metal GPU (FP16) | 59.61% | 34.58% | -0.25 | — | — | 85.8 | ~87 | [v-c75](https://edgefirst.studio/public/validation/v-c75/details?mode=charts) |
132
- | Small | Apple iPhone 17 Pro — CoreML CPU (FP16) | 59.56% | 34.55% | -0.28 | — | — | 31.9 | ~32 | [v-c6e](https://edgefirst.studio/public/validation/v-c6e/details?mode=charts) |
133
- | Small | Apple iPhone 15 Pro — CoreML Neural Engine (FP16) | 59.63% | 34.63% | -0.20 | — | — | 139.2 | ~171 | [v-c34](https://edgefirst.studio/public/validation/v-c34/details?mode=charts) |
134
- | Small | Apple iPhone 15 Pro — CoreML Metal GPU (FP16) | 59.62% | 34.59% | -0.24 | — | — | 24.8 | ~25 | [v-c42](https://edgefirst.studio/public/validation/v-c42/details?mode=charts) |
135
- | Small | Apple iPhone 15 Pro — CoreML CPU (FP16) | 59.57% | 34.55% | -0.28 | — | — | 27.1 | ~27 | [v-c3b](https://edgefirst.studio/public/validation/v-c3b/details?mode=charts) |
136
  | Small | NXP i.MX 8M Plus + VeriSilicon NPU (FRDM) | 58.45% | 33.86% | -0.97 | 147.05 | 226.42 | 6.3 | ~7 | [v-972](https://edgefirst.studio/public/validation/v-972/details?mode=charts) |
 
 
137
  | Small | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — latency | 58.42% | 33.76% | -1.07 | 51.16 | 112.09 | 18.3 | ~19 | [v-941](https://edgefirst.studio/public/validation/v-941/details?mode=charts) |
138
  | Small | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 58.42% | 33.76% | -1.07 | 194.35 | 262.79 | 19.8 | ~20 | [v-943](https://edgefirst.studio/public/validation/v-943/details?mode=charts) |
139
  | Small | NXP i.MX 95 + eIQ Neutron NPU (Phytec) — throughput | 58.42% | 33.76% | -1.07 | 185.95 | 245.69 | 20.8 | ~21 | [v-8fd](https://edgefirst.studio/public/validation/v-8fd/details?mode=charts) |
140
- | Small | NXP i.MX 95 + eIQ Neutron NPU (Verdin) — latency | 45.84% | 27.17% | -7.66 ⚠ | 77.67 | 99.84 | 12.5 | ~13 | [v-bdd](https://edgefirst.studio/public/validation/v-bdd/details?mode=charts) |
141
- | Small | NXP i.MX 95 + eIQ Neutron NPU (Verdin) — throughput | 59.07% | 34.06% | -0.77 | 50.50 | 106.67 | 18.8 | ~19 | [v-bdc](https://edgefirst.studio/public/validation/v-bdc/details?mode=charts) |
142
  | Small | NXP Ara240 (FRDM) — latency | 56.31% | 32.62% | -2.21 | 15.64 | 42.24 | 53.6 | ~54 | [v-a26](https://edgefirst.studio/public/validation/v-a26/details?mode=charts) |
143
  | Small | NXP Ara240 (FRDM) — throughput | 56.32% | 32.63% | -2.20 | 16.15 | 66.47 | 64.7 | ~94 | [v-a27](https://edgefirst.studio/public/validation/v-a27/details?mode=charts) |
144
  | Small | Raspberry Pi 5 + Hailo-8L NPU | 58.40% | 33.68% | -1.15 | 42.29 | 61.72 | 22.7 | ~23 | [v-8ef](https://edgefirst.studio/public/validation/v-8ef/details?mode=charts) |
@@ -149,18 +153,20 @@ Row conventions in the table below:
149
  | Medium | Apple M2 Max — CoreML Neural Engine (FP16) | 63.08% | 37.10% | -1.05 | 17.13 | 23.51 | 111.3 | ~111 | [v-72e](https://edgefirst.studio/public/validation/v-72e/details?mode=charts) |
150
  | Medium | Apple M2 Max — CoreML Metal GPU (FP16) | 64.09% | 37.54% | -0.61 | 50.64 | 58.53 | 58.0 | ~58 | [v-9df](https://edgefirst.studio/public/validation/v-9df/details?mode=charts) |
151
  | Medium | Apple M2 Max — CoreML CPU (FP16) | 64.07% | 37.51% | -0.64 | 78.49 | 86.82 | 25.1 | ~25 | [v-9de](https://edgefirst.studio/public/validation/v-9de/details?mode=charts) |
152
- | Medium | Apple iPhone 17 Pro — CoreML Neural Engine (FP16) | 64.05% | 37.62% | -0.53 | — | — | 94.0 | ~95 | [v-c66](https://edgefirst.studio/public/validation/v-c66/details?mode=charts) |
153
- | Medium | Apple iPhone 17 Pro — CoreML Metal GPU (FP16) | 64.09% | 37.55% | -0.60 | — | — | 30.9 | ~31 | [v-c74](https://edgefirst.studio/public/validation/v-c74/details?mode=charts) |
154
- | Medium | Apple iPhone 17 Pro — CoreML CPU (FP16) | 64.06% | 37.51% | -0.64 | — | — | 12.7 | ~13 | [v-c6d](https://edgefirst.studio/public/validation/v-c6d/details?mode=charts) |
155
- | Medium | Apple iPhone 15 Pro — CoreML Neural Engine (FP16) | 64.05% | 37.62% | -0.53 | — | — | 79.0 | ~80 | [v-c33](https://edgefirst.studio/public/validation/v-c33/details?mode=charts) |
156
- | Medium | Apple iPhone 15 Pro — CoreML Metal GPU (FP16) | 64.10% | 37.53% | -0.62 | — | — | 11.3 | ~11 | [v-c41](https://edgefirst.studio/public/validation/v-c41/details?mode=charts) |
157
- | Medium | Apple iPhone 15 Pro — CoreML CPU (FP16) | 64.06% | 37.53% | -0.62 | — | — | 10.5 | ~11 | [v-c3a](https://edgefirst.studio/public/validation/v-c3a/details?mode=charts) |
158
  | Medium | NXP i.MX 8M Plus + VeriSilicon NPU (FRDM) | 62.77% | 36.63% | -1.52 | 267.65 | 343.19 | 3.6 | ~4 | [v-9a8](https://edgefirst.studio/public/validation/v-9a8/details?mode=charts) |
 
 
159
  | Medium | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — latency | 62.66% | 36.61% | -1.54 | 127.25 | 177.98 | 7.6 | ~8 | [v-98f](https://edgefirst.studio/public/validation/v-98f/details?mode=charts) |
160
  | Medium | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 62.66% | 36.61% | -1.54 | 495.23 | 548.82 | 8.0 | ~8 | [v-991](https://edgefirst.studio/public/validation/v-991/details?mode=charts) |
161
  | Medium | NXP i.MX 95 + eIQ Neutron NPU (Phytec) — throughput | 62.66% | 36.61% | -1.54 | 484.09 | 531.70 | 8.2 | ~8 | [v-959](https://edgefirst.studio/public/validation/v-959/details?mode=charts) |
162
- | Medium | NXP i.MX 95 + eIQ Neutron NPU (Verdin) — latency | 64.22% | 37.49% | -0.66 | 125.57 | 187.38 | 7.8 | ~8 | [v-b34](https://edgefirst.studio/public/validation/v-b34/details?mode=charts) |
163
- | Medium | NXP i.MX 95 + eIQ Neutron NPU (Verdin) — throughput | 64.23% | 37.49% | -0.66 | 125.58 | 187.77 | 7.8 | ~8 | [v-bea](https://edgefirst.studio/public/validation/v-bea/details?mode=charts) |
164
  | Medium | NXP Ara240 (FRDM) — latency | 58.60% | 34.00% | -4.15 | 31.02 | 53.88 | 30.9 | ~31 | [v-a34](https://edgefirst.studio/public/validation/v-a34/details?mode=charts) |
165
  | Medium | NXP Ara240 (FRDM) — throughput | 58.59% | 33.99% | -4.16 | 31.15 | 55.73 | 38.1 | ~38 | [v-a35](https://edgefirst.studio/public/validation/v-a35/details?mode=charts) |
166
  | Medium | Raspberry Pi 5 + Hailo-8L NPU | 63.27% | 37.03% | -1.12 | 66.60 | 86.17 | 13.3 | ~13 | [v-931](https://edgefirst.studio/public/validation/v-931/details?mode=charts) |
 
105
  | Nano | Apple M2 Max — CoreML Neural Engine (FP16) | 49.88% | 28.46% | -0.68 | 2.74 | 10.21 | 422.9 | ~424 | [v-72c](https://edgefirst.studio/public/validation/v-72c/details?mode=charts) |
106
  | Nano | Apple M2 Max — CoreML Metal GPU (FP16) | 49.94% | 28.47% | -0.67 | 6.64 | 16.93 | 307.1 | ~307 | [v-736](https://edgefirst.studio/public/validation/v-736/details?mode=charts) |
107
  | Nano | Apple M2 Max — CoreML CPU (FP16) | 50.78% | 28.92% | -0.22 | 21.74 | 29.90 | 87.2 | ~87 | [v-9f4](https://edgefirst.studio/public/validation/v-9f4/details?mode=charts) |
108
+ | Nano | Apple iPhone 17 Pro — CoreML Neural Engine (FP16) | 51.14% | 29.20% | +0.06 | 2.69 | 26.82 | 160.3 | ~429 | [v-c06](https://edgefirst.studio/public/validation/v-c06/details?mode=charts) |
109
+ | Nano | Apple iPhone 17 Pro — CoreML Metal GPU (FP16) | 51.14% | 29.14% | +0.00 | 12.79 | 34.96 | 121.4 | ~136 | [v-c04](https://edgefirst.studio/public/validation/v-c04/details?mode=charts) |
110
+ | Nano | Apple iPhone 17 Pro — CoreML CPU (FP16) | 51.15% | 29.16% | +0.02 | 29.51 | 42.41 | 64.8 | ~67 | [v-c03](https://edgefirst.studio/public/validation/v-c03/details?mode=charts) |
111
+ | Nano | Apple iPhone 15 Pro — CoreML Neural Engine (FP16) | 51.13% | 29.19% | +0.05 | 3.01 | 36.39 | 117.8 | ~375 | [v-c0c](https://edgefirst.studio/public/validation/v-c0c/details?mode=charts) |
112
+ | Nano | Apple iPhone 15 Pro — CoreML Metal GPU (FP16) | 51.14% | 29.15% | +0.01 | 22.02 | 59.78 | 73.3 | ~80 | [v-c0a](https://edgefirst.studio/public/validation/v-c0a/details?mode=charts) |
113
+ | Nano | Apple iPhone 15 Pro — CoreML CPU (FP16) | 51.14% | 29.16% | +0.02 | 38.86 | 57.61 | 49.0 | ~51 | [v-c08](https://edgefirst.studio/public/validation/v-c08/details?mode=charts) |
114
  | Nano | NXP i.MX 8M Plus + VeriSilicon NPU (FRDM) | 48.83% | 27.59% | -1.55 | 79.61 | 199.44 | 10.6 | ~12 | [v-8d7](https://edgefirst.studio/public/validation/v-8d7/details?mode=charts) |
115
+ | Nano | NXP i.MX 8M Plus + VeriSilicon NPU (Verdin) — latency | 37.94% | 21.74% | -7.40 ⚠ | 83.28 | 135.65 | 10.5 | ~12 | [v-c84](https://edgefirst.studio/public/validation/v-c84/details?mode=charts) |
116
+ | Nano | NXP i.MX 8M Plus + VeriSilicon NPU (Verdin) — throughput | 48.83% | 27.59% | -1.55 | 79.26 | 217.40 | 10.4 | ~12 | [v-c83](https://edgefirst.studio/public/validation/v-c83/details?mode=charts) |
117
  | Nano | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — latency | 48.87% | 27.63% | -1.51 | 20.62 | 116.40 | 20.8 | ~13 | [v-8cf](https://edgefirst.studio/public/validation/v-8cf/details?mode=charts) |
118
  | Nano | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 38.09% | 21.84% | -7.30 ⚠ | 93.69 | 139.74 | 39.9 | ~40 | [v-8ce](https://edgefirst.studio/public/validation/v-8ce/details?mode=charts) |
119
  | Nano | NXP i.MX 95 + eIQ Neutron NPU (Phytec) — throughput | 48.87% | 27.63% | -1.51 | 24.83 | 166.24 | 23.7 | ~24 | [v-8a8](https://edgefirst.studio/public/validation/v-8a8/details?mode=charts) |
120
+ | Nano | NXP i.MX 95 + eIQ Neutron NPU (Verdin) — latency | 49.62% | 27.96% | -1.18 | 20.85 | 123.54 | 21.3 | ~14 | [v-e26](https://edgefirst.studio/public/validation/v-e26/details?mode=charts) |
121
+ | Nano | NXP i.MX 95 + eIQ Neutron NPU (Verdin) — throughput | 49.63% | 27.97% | -1.17 | 25.98 | 199.50 | 22.6 | ~23 | [v-e0d](https://edgefirst.studio/public/validation/v-e0d/details?mode=charts) |
122
  | Nano | NXP Ara240 (FRDM) — latency | 47.22% | 26.62% | -2.52 | 9.63 | 42.97 | 50.4 | ~56 | [v-a18](https://edgefirst.studio/public/validation/v-a18/details?mode=charts) |
123
  | Nano | NXP Ara240 (FRDM) — throughput | 47.22% | 26.62% | -2.52 | 9.80 | 62.62 | 51.7 | ~226 | [v-a19](https://edgefirst.studio/public/validation/v-a19/details?mode=charts) |
124
  | Nano | Raspberry Pi 5 + Hailo-8L NPU | 49.28% | 28.02% | -1.12 | 16.18 | 38.25 | 53.7 | ~54 | [v-8e5](https://edgefirst.studio/public/validation/v-8e5/details?mode=charts) |
 
129
  | Small | Apple M2 Max — CoreML Neural Engine (FP16) | 59.62% | 34.65% | -0.18 | 6.18 | 13.83 | 261.8 | ~262 | [v-9e9](https://edgefirst.studio/public/validation/v-9e9/details?mode=charts) |
130
  | Small | Apple M2 Max — CoreML Metal GPU (FP16) | 59.61% | 34.58% | -0.25 | 21.34 | 29.86 | 133.8 | ~134 | [v-9e8](https://edgefirst.studio/public/validation/v-9e8/details?mode=charts) |
131
  | Small | Apple M2 Max — CoreML CPU (FP16) | 59.57% | 34.54% | -0.29 | 41.25 | 49.04 | 47.0 | ~47 | [v-9e7](https://edgefirst.studio/public/validation/v-9e7/details?mode=charts) |
132
+ | Small | Apple iPhone 17 Pro — CoreML Neural Engine (FP16) | 59.63% | 34.62% | -0.21 | 7.42 | 22.21 | 186.5 | ~199 | [v-c67](https://edgefirst.studio/public/validation/v-c67/details?mode=charts) |
133
+ | Small | Apple iPhone 17 Pro — CoreML Metal GPU (FP16) | 59.61% | 34.58% | -0.25 | 21.87 | 33.30 | 85.8 | ~87 | [v-c75](https://edgefirst.studio/public/validation/v-c75/details?mode=charts) |
134
+ | Small | Apple iPhone 17 Pro — CoreML CPU (FP16) | 59.56% | 34.55% | -0.28 | 61.34 | 77.09 | 31.9 | ~32 | [v-c6e](https://edgefirst.studio/public/validation/v-c6e/details?mode=charts) |
135
+ | Small | Apple iPhone 15 Pro — CoreML Neural Engine (FP16) | 59.63% | 34.63% | -0.20 | 7.15 | 31.40 | 139.2 | ~171 | [v-c34](https://edgefirst.studio/public/validation/v-c34/details?mode=charts) |
136
+ | Small | Apple iPhone 15 Pro — CoreML Metal GPU (FP16) | 59.62% | 34.59% | -0.24 | 78.73 | 93.16 | 24.8 | ~25 | [v-c42](https://edgefirst.studio/public/validation/v-c42/details?mode=charts) |
137
+ | Small | Apple iPhone 15 Pro — CoreML CPU (FP16) | 59.57% | 34.55% | -0.28 | 71.81 | 93.60 | 27.1 | ~27 | [v-c3b](https://edgefirst.studio/public/validation/v-c3b/details?mode=charts) |
138
  | Small | NXP i.MX 8M Plus + VeriSilicon NPU (FRDM) | 58.45% | 33.86% | -0.97 | 147.05 | 226.42 | 6.3 | ~7 | [v-972](https://edgefirst.studio/public/validation/v-972/details?mode=charts) |
139
+ | Small | NXP i.MX 8M Plus + VeriSilicon NPU (Verdin) — latency | 45.39% | 26.94% | -7.89 ⚠ | 151.70 | 203.35 | 6.1 | ~7 | [v-c93](https://edgefirst.studio/public/validation/v-c93/details?mode=charts) |
140
+ | Small | NXP i.MX 8M Plus + VeriSilicon NPU (Verdin) — throughput | 58.45% | 33.86% | -0.97 | 146.93 | 239.32 | 6.3 | ~7 | [v-c92](https://edgefirst.studio/public/validation/v-c92/details?mode=charts) |
141
  | Small | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — latency | 58.42% | 33.76% | -1.07 | 51.16 | 112.09 | 18.3 | ~19 | [v-941](https://edgefirst.studio/public/validation/v-941/details?mode=charts) |
142
  | Small | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 58.42% | 33.76% | -1.07 | 194.35 | 262.79 | 19.8 | ~20 | [v-943](https://edgefirst.studio/public/validation/v-943/details?mode=charts) |
143
  | Small | NXP i.MX 95 + eIQ Neutron NPU (Phytec) — throughput | 58.42% | 33.76% | -1.07 | 185.95 | 245.69 | 20.8 | ~21 | [v-8fd](https://edgefirst.studio/public/validation/v-8fd/details?mode=charts) |
144
+ | Small | NXP i.MX 95 + eIQ Neutron NPU (Verdin) — latency | 59.07% | 34.06% | -0.77 | 50.53 | 105.70 | 18.8 | ~19 | [v-e27](https://edgefirst.studio/public/validation/v-e27/details?mode=charts) |
145
+ | Small | NXP i.MX 95 + eIQ Neutron NPU (Verdin) — throughput | 59.07% | 34.06% | -0.77 | 388.03 | 450.48 | 20.3 | ~20 | [v-e14](https://edgefirst.studio/public/validation/v-e14/details?mode=charts) |
146
  | Small | NXP Ara240 (FRDM) — latency | 56.31% | 32.62% | -2.21 | 15.64 | 42.24 | 53.6 | ~54 | [v-a26](https://edgefirst.studio/public/validation/v-a26/details?mode=charts) |
147
  | Small | NXP Ara240 (FRDM) — throughput | 56.32% | 32.63% | -2.20 | 16.15 | 66.47 | 64.7 | ~94 | [v-a27](https://edgefirst.studio/public/validation/v-a27/details?mode=charts) |
148
  | Small | Raspberry Pi 5 + Hailo-8L NPU | 58.40% | 33.68% | -1.15 | 42.29 | 61.72 | 22.7 | ~23 | [v-8ef](https://edgefirst.studio/public/validation/v-8ef/details?mode=charts) |
 
153
  | Medium | Apple M2 Max — CoreML Neural Engine (FP16) | 63.08% | 37.10% | -1.05 | 17.13 | 23.51 | 111.3 | ~111 | [v-72e](https://edgefirst.studio/public/validation/v-72e/details?mode=charts) |
154
  | Medium | Apple M2 Max — CoreML Metal GPU (FP16) | 64.09% | 37.54% | -0.61 | 50.64 | 58.53 | 58.0 | ~58 | [v-9df](https://edgefirst.studio/public/validation/v-9df/details?mode=charts) |
155
  | Medium | Apple M2 Max — CoreML CPU (FP16) | 64.07% | 37.51% | -0.64 | 78.49 | 86.82 | 25.1 | ~25 | [v-9de](https://edgefirst.studio/public/validation/v-9de/details?mode=charts) |
156
+ | Medium | Apple iPhone 17 Pro — CoreML Neural Engine (FP16) | 64.05% | 37.62% | -0.53 | 20.30 | 28.94 | 94.0 | ~95 | [v-c66](https://edgefirst.studio/public/validation/v-c66/details?mode=charts) |
157
+ | Medium | Apple iPhone 17 Pro — CoreML Metal GPU (FP16) | 64.09% | 37.55% | -0.60 | 63.36 | 73.22 | 30.9 | ~31 | [v-c74](https://edgefirst.studio/public/validation/v-c74/details?mode=charts) |
158
+ | Medium | Apple iPhone 17 Pro — CoreML CPU (FP16) | 64.06% | 37.51% | -0.64 | 155.66 | 171.81 | 12.7 | ~13 | [v-c6d](https://edgefirst.studio/public/validation/v-c6d/details?mode=charts) |
159
+ | Medium | Apple iPhone 15 Pro — CoreML Neural Engine (FP16) | 64.05% | 37.62% | -0.53 | 23.84 | 35.72 | 79.0 | ~80 | [v-c33](https://edgefirst.studio/public/validation/v-c33/details?mode=charts) |
160
+ | Medium | Apple iPhone 15 Pro — CoreML Metal GPU (FP16) | 64.10% | 37.53% | -0.62 | 172.63 | 190.72 | 11.3 | ~11 | [v-c41](https://edgefirst.studio/public/validation/v-c41/details?mode=charts) |
161
+ | Medium | Apple iPhone 15 Pro — CoreML CPU (FP16) | 64.06% | 37.53% | -0.62 | 187.36 | 212.79 | 10.5 | ~11 | [v-c3a](https://edgefirst.studio/public/validation/v-c3a/details?mode=charts) |
162
  | Medium | NXP i.MX 8M Plus + VeriSilicon NPU (FRDM) | 62.77% | 36.63% | -1.52 | 267.65 | 343.19 | 3.6 | ~4 | [v-9a8](https://edgefirst.studio/public/validation/v-9a8/details?mode=charts) |
163
+ | Medium | NXP i.MX 8M Plus + VeriSilicon NPU (Verdin) — latency | 46.05% | 27.68% | -10.47 ⚠ | 276.12 | 327.36 | 3.5 | ~4 | [v-ca7](https://edgefirst.studio/public/validation/v-ca7/details?mode=charts) |
164
+ | Medium | NXP i.MX 8M Plus + VeriSilicon NPU (Verdin) — throughput | 62.77% | 36.63% | -1.52 | 270.51 | 363.03 | 3.6 | ~4 | [v-ca6](https://edgefirst.studio/public/validation/v-ca6/details?mode=charts) |
165
  | Medium | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — latency | 62.66% | 36.61% | -1.54 | 127.25 | 177.98 | 7.6 | ~8 | [v-98f](https://edgefirst.studio/public/validation/v-98f/details?mode=charts) |
166
  | Medium | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 62.66% | 36.61% | -1.54 | 495.23 | 548.82 | 8.0 | ~8 | [v-991](https://edgefirst.studio/public/validation/v-991/details?mode=charts) |
167
  | Medium | NXP i.MX 95 + eIQ Neutron NPU (Phytec) — throughput | 62.66% | 36.61% | -1.54 | 484.09 | 531.70 | 8.2 | ~8 | [v-959](https://edgefirst.studio/public/validation/v-959/details?mode=charts) |
168
+ | Medium | NXP i.MX 95 + eIQ Neutron NPU (Verdin) — latency | 64.23% | 37.49% | -0.66 | 125.61 | 188.01 | 7.8 | ~8 | [v-e28](https://edgefirst.studio/public/validation/v-e28/details?mode=charts) |
169
+ | Medium | NXP i.MX 95 + eIQ Neutron NPU (Verdin) — throughput | 64.22% | 37.49% | -0.66 | 983.05 | 1044.65 | 8.1 | ~8 | [v-e1b](https://edgefirst.studio/public/validation/v-e1b/details?mode=charts) |
170
  | Medium | NXP Ara240 (FRDM) — latency | 58.60% | 34.00% | -4.15 | 31.02 | 53.88 | 30.9 | ~31 | [v-a34](https://edgefirst.studio/public/validation/v-a34/details?mode=charts) |
171
  | Medium | NXP Ara240 (FRDM) — throughput | 58.59% | 33.99% | -4.16 | 31.15 | 55.73 | 38.1 | ~38 | [v-a35](https://edgefirst.studio/public/validation/v-a35/details?mode=charts) |
172
  | Medium | Raspberry Pi 5 + Hailo-8L NPU | 63.27% | 37.03% | -1.12 | 66.60 | 86.17 | 13.3 | ~13 | [v-931](https://edgefirst.studio/public/validation/v-931/details?mode=charts) |