v0.47.0
Browse filesSee https://github.com/quic/ai-hub-models/releases/v0.47.0 for changelog.
README.md
CHANGED
|
@@ -27,9 +27,9 @@ Below are pre-exported model assets ready for deployment.
|
|
| 27 |
|
| 28 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 29 |
|---|---|---|---|---|
|
| 30 |
-
| ONNX | float | Universal | QAIRT 2.
|
| 31 |
-
| QNN_DLC | float | Universal | QAIRT 2.
|
| 32 |
-
| TFLITE | float | Universal | QAIRT 2.
|
| 33 |
|
| 34 |
For more device-specific assets and performance metrics, visit **[Nomic-Embed-Text on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/nomic_embed_text)**.
|
| 35 |
|
|
@@ -58,33 +58,35 @@ See our repository for [Nomic-Embed-Text on GitHub](https://github.com/quic/ai-h
|
|
| 58 |
## Performance Summary
|
| 59 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 60 |
|---|---|---|---|---|---|---
|
| 61 |
-
| Nomic-Embed-Text | ONNX | float | Snapdragon® X Elite | 8.
|
| 62 |
-
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.
|
| 63 |
-
| Nomic-Embed-Text | ONNX | float | Qualcomm® QCS8550 (Proxy) |
|
| 64 |
-
| Nomic-Embed-Text | ONNX | float | Qualcomm® QCS9075 |
|
| 65 |
-
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.
|
| 66 |
-
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile |
|
| 67 |
-
| Nomic-Embed-Text |
|
| 68 |
-
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon®
|
| 69 |
-
| Nomic-Embed-Text | QNN_DLC | float |
|
| 70 |
-
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm®
|
| 71 |
-
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm®
|
| 72 |
-
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm®
|
| 73 |
-
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm®
|
| 74 |
-
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm®
|
| 75 |
-
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm®
|
| 76 |
-
| Nomic-Embed-Text | QNN_DLC | float |
|
| 77 |
-
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Elite
|
| 78 |
-
| Nomic-Embed-Text |
|
| 79 |
-
| Nomic-Embed-Text |
|
| 80 |
-
| Nomic-Embed-Text | TFLITE | float |
|
| 81 |
-
| Nomic-Embed-Text | TFLITE | float | Qualcomm®
|
| 82 |
-
| Nomic-Embed-Text | TFLITE | float | Qualcomm®
|
| 83 |
-
| Nomic-Embed-Text | TFLITE | float | Qualcomm®
|
| 84 |
-
| Nomic-Embed-Text | TFLITE | float | Qualcomm®
|
| 85 |
-
| Nomic-Embed-Text | TFLITE | float | Qualcomm®
|
| 86 |
-
| Nomic-Embed-Text | TFLITE | float |
|
| 87 |
-
| Nomic-Embed-Text | TFLITE | float |
|
|
|
|
|
|
|
| 88 |
|
| 89 |
## License
|
| 90 |
* The license for the original implementation of Nomic-Embed-Text can be found
|
|
|
|
| 27 |
|
| 28 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 29 |
|---|---|---|---|---|
|
| 30 |
+
| ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/nomic_embed_text/releases/v0.47.0/nomic_embed_text-onnx-float.zip)
|
| 31 |
+
| QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/nomic_embed_text/releases/v0.47.0/nomic_embed_text-qnn_dlc-float.zip)
|
| 32 |
+
| TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/nomic_embed_text/releases/v0.47.0/nomic_embed_text-tflite-float.zip)
|
| 33 |
|
| 34 |
For more device-specific assets and performance metrics, visit **[Nomic-Embed-Text on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/nomic_embed_text)**.
|
| 35 |
|
|
|
|
| 58 |
## Performance Summary
|
| 59 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 60 |
|---|---|---|---|---|---|---
|
| 61 |
+
| Nomic-Embed-Text | ONNX | float | Snapdragon® X Elite | 8.501 ms | 263 - 263 MB | NPU
|
| 62 |
+
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.575 ms | 0 - 461 MB | NPU
|
| 63 |
+
| Nomic-Embed-Text | ONNX | float | Qualcomm® QCS8550 (Proxy) | 7.931 ms | 0 - 324 MB | NPU
|
| 64 |
+
| Nomic-Embed-Text | ONNX | float | Qualcomm® QCS9075 | 10.524 ms | 0 - 3 MB | NPU
|
| 65 |
+
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.302 ms | 0 - 418 MB | NPU
|
| 66 |
+
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.876 ms | 0 - 416 MB | NPU
|
| 67 |
+
| Nomic-Embed-Text | ONNX | float | Snapdragon® X2 Elite | 3.584 ms | 263 - 263 MB | NPU
|
| 68 |
+
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® X Elite | 8.034 ms | 0 - 0 MB | NPU
|
| 69 |
+
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.318 ms | 0 - 445 MB | NPU
|
| 70 |
+
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 28.351 ms | 0 - 415 MB | NPU
|
| 71 |
+
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 7.473 ms | 0 - 2 MB | NPU
|
| 72 |
+
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA8775P | 9.709 ms | 0 - 416 MB | NPU
|
| 73 |
+
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS9075 | 10.482 ms | 2 - 4 MB | NPU
|
| 74 |
+
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 10.958 ms | 0 - 428 MB | NPU
|
| 75 |
+
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA7255P | 28.351 ms | 0 - 415 MB | NPU
|
| 76 |
+
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA8295P | 10.624 ms | 0 - 397 MB | NPU
|
| 77 |
+
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.401 ms | 0 - 412 MB | NPU
|
| 78 |
+
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.899 ms | 0 - 411 MB | NPU
|
| 79 |
+
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® X2 Elite | 3.896 ms | 1 - 1 MB | NPU
|
| 80 |
+
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.305 ms | 0 - 451 MB | NPU
|
| 81 |
+
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 28.331 ms | 0 - 419 MB | NPU
|
| 82 |
+
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 7.311 ms | 0 - 3 MB | NPU
|
| 83 |
+
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8775P | 9.714 ms | 0 - 419 MB | NPU
|
| 84 |
+
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS9075 | 10.61 ms | 0 - 265 MB | NPU
|
| 85 |
+
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 10.937 ms | 0 - 426 MB | NPU
|
| 86 |
+
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA7255P | 28.331 ms | 0 - 419 MB | NPU
|
| 87 |
+
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8295P | 10.622 ms | 0 - 398 MB | NPU
|
| 88 |
+
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.374 ms | 0 - 417 MB | NPU
|
| 89 |
+
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.877 ms | 0 - 418 MB | NPU
|
| 90 |
|
| 91 |
## License
|
| 92 |
* The license for the original implementation of Nomic-Embed-Text can be found
|