Card: add a measured Performance table (Pixel 8a, benchmark_model GPU+CPU), naming the runtime for each row

README.md

@@ -62,3 +62,17 @@ var score = 0f; for (i in 0 until 10) score += (i + 1) * dist[i]   // 1-10
 [idealo/image-quality-assessment](https://github.com/idealo/image-quality-assessment) (Apache-2.0) —
 NIMA MobileNet aesthetic + technical weights. Paper: *NIMA: Neural Image Assessment* (Talebi &
 Milanfar, 2018).
+
+## Performance
+
+Measured on a **Pixel 8a** (Tensor G3, Android 16) with the standard TFLite [`benchmark_model`](https://ai.google.dev/edge/litert/models/measurement) tool — 10 warm-up runs then 50 timed runs, reported as the tool's mean.
+
+| Runtime | Backend | Graph on GPU | Latency |
+|---|---|---|---|
+| TFLite `benchmark_model` (`TfLiteGpuDelegateV2`) — `nima_aesthetic_fp16.tflite` | GPU (OpenCL) | 86 / 86 | 11.3 ms |
+| TFLite `benchmark_model` (`TfLiteGpuDelegateV2`) — `nima_technical_fp16.tflite` | GPU (OpenCL) | 86 / 86 | 10.9 ms |
+| TFLite `benchmark_model` — `nima_aesthetic_fp16.tflite` | CPU (XNNPACK, 4 threads) | — | 18.5 ms |
+| TFLite `benchmark_model` — `nima_technical_fp16.tflite` | CPU (XNNPACK, 4 threads) | — | 18.5 ms |
+
+**Any on-device figure recorded when this model shipped came from a different runtime.** It was taken through LiteRT's own `CompiledModel` accelerator (logcat reports it as `LITERT_CL`), which is the path the Kotlin sample app and the LiteRT API use, and it appears elsewhere on this card. The rows above are the classic TFLite OpenCL delegate, measured with a tool anyone can download and re-run. The two are not comparable, so read the rows above as a reproducible floor rather than as this model's speed on LiteRT.
+