Add measured performance section (M4 Max)

Thanks for converting Qwen2.5-Coder-3B — it answers correctly on both backends. This PR adds a measured Performance section to the card. Measured with the litert-lm CLI (`benchmark -p 256 -d 256 --runs 3 --cache no`) on an idle Apple M4 Max, generation-gated first (the backend produced correct text before any number was recorded). Happy to adjust the format if you'd like these to read differently.

README.md

@@ -25,4 +25,15 @@ This repository contains LiteRT-LM variant of [Qwen/Qwen2.5-Coder-3B-Instruct](h
 
 ## Integration
 
-Ready to integrate this into your product? Get started in the [LiteRT-LM documentation](https://ai.google.dev/edge/litert-lm/overview).
+Ready to integrate this into your product? Get started in the [LiteRT-LM documentation](https://ai.google.dev/edge/litert-lm/overview).
+
+## Performance (Apple M4 Max, measured)
+
+Measured with the LiteRT-LM CLI: `litert-lm benchmark -p 256 -d 256 --runs 3 --cache no`
+(litert-lm 0.15.0) on an idle Apple M4 Max (macOS); 256 prefill / 256 decode tokens, 3 iterations
+averaged by the tool. A desktop reference point — phone-side figures vary by SoC and backend.
+
+| Backend | Prefill (tokens/s) | Decode (tokens/s) | Time-to-first-token (s) |
+|---|---|---|---|
+| CPU | 121 | 26.7 | 2.16 |
+| GPU | 1,320 | 77.8 | 0.21 |