README: EXPERIMENTAL int8 bundle

README.md

@@ -37,3 +37,32 @@ Core AI cannot execute on Linux; the on-device parity gate runs on macOS against
 Derivative of EmbeddingGemma; use is subject to the
 [Gemma Terms of Use](https://ai.google.dev/gemma/terms) and the
 [Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy).
+
+
+## EXPERIMENTAL - int8 graph-compressed bundle (`int8/`)
+
+> **EXPERIMENTAL. Do not use for production embeddings until vector-parity has been
+> qualified on a Mac against the fp32 bundle above.** No numerics gate has been run on
+> this artifact: the conversion box is Linux with no GPU delegate, so nothing here has
+> produced a vector.
+
+`int8/embeddinggemma-300m_int8_static.aimodel` is the fp32 bundle in
+`model/` (this repo @ `2bee70c5bc49cafc3c9e7f88d4d0095508cbfd4b`) put through **`coreai_opt.coreai_utils.quantize_weights`
+with `dtype=INT8`** - a Core AI *graph* compression pass that rewrites the weight
+constants of an existing `.aimodel` in place. There is **no PyTorch round-trip and no
+re-export**: the graph, the input signature (`seq_len 256`, 768-d output) and the
+tokenizer are the fp32 bundle's.
+
+| | fp32 (`model/`) | int8 (`int8/`) |
+|---|---|---|
+| `main.mlirb` | 1,244,157,766 B | 323,252,231 B |
+| ratio | 1.00x | **0.26x** |
+| producer | `coreai-core 1.0.0b2` | `coreai-core 1.0.0b2` |
+
+The `reference.json` and `tokenizer/` beside it are byte-identical copies of the fp32
+bundle's, carried so the folder is self-contained.
+
+**Qualification gate before any use:** embed a fixed corpus with both bundles on a Mac
+and compare vectors (cosine similarity per vector and retrieval-rank agreement), not
+just spot-check output shapes. fp16 embeddinggemma is already known to fail vector
+precision parity; int8 has not been shown to pass.