Update model card footprint and quantization notes

README.md

@@ -40,6 +40,7 @@ locally; no network request is required by the SDK or demo app.
 | `dist/ASRModels.bundle` | Prebuilt model assets: Core ML audio tower, ONNX decoder, tokenizer tables, and integrity manifest |
 | `ASRDemo/` | Minimal iOS app for microphone recording and one-shot transcription |
 | `ANEBench/` | Optional iOS app for Core ML / ANE latency and sustained-load checks |
+| `assets/` | Screenshots and model-card media |
 | `GETTING_STARTED.md` | Reproducible setup, build, signing, and device-testing guide |
 | `LICENSE` | Apache License 2.0 |
 
@@ -48,6 +49,27 @@ locally; no network request is required by the SDK or demo app.
 - [Audio8-ASR-0.1B](https://huggingface.co/AutoArk-AI/Audio8-ASR-0.1B): base model checkpoint.
 - [Audio8-ASR-0.1B-onnx-runtime](https://huggingface.co/AutoArk-AI/Audio8-ASR-0.1B-onnx-runtime): ONNX Runtime package.
 
+## Packaged Model Variant and Footprint
+
+This release packages the iPhone ANE-oriented variant of `Audio8-ASR-0.1B`:
+
+- Audio tower/head: compiled Core ML `mlmodelc` with mixed Float16/Int8
+  storage, Float16 compute/output tensors, and ANE execution.
+- Decoder: ONNX Runtime CPU decoder with int4 shared language-model weights
+  (`lm_shared_int4.data`) and int4 prefill/decode ONNX graphs.
+- Token embedding table: Float16 (`token_embedding_fp16.bin`).
+
+On a physical iPhone with the Core ML audio tower running on ANE, the demo is
+designed to keep runtime memory footprint around 200 MB. The example below
+shows a 183 MB app footprint during a microphone transcription run, with sampled
+peak footprint varying by device, iOS version, cold/warm start state, and
+measurement window. We position this package as one of the smallest usable ASR
+model stacks for on-device iPhone transcription.
+
+<p align="center">
+  <img src="assets/iphone-asr-demo-footprint.png" alt="Audio8 ASR iPhone demo memory footprint" width="360">
+</p>
+
 ## Quick Start
 
 ```bash