Card: add 'Reproduce (official tools only)' section

README.md

@@ -74,6 +74,28 @@ standard `LlamaForCausalLM` architecture, so it rides the existing converter and
 runtime with no custom code. Blockwise (not channelwise) int4 is what preserves
 reasoning accuracy.
 
+## Reproduce (official tools only)
+
+Built with **stock `litert-torch`** — no custom code, no graph patches. The only
+non-default choice is the int4 recipe: the tool's default named int4 is
+*channelwise* (which degrades small models), so this uses **blockwise-128** (the
+scheme the official models ship), passed as a recipe file to the standard export:
+
+```python
+from litert_torch.generative.export_hf.export import export
+export(
+    model="tiiuae/Falcon3-3B-Instruct",
+    output_dir="out",
+    quantization_recipe="falcon_int4_block128.json",  # included in this repo
+    cache_length=2048,
+    trust_remote_code=True,
+)
+```
+
+`falcon_int4_block128.json` is included in this repo. (If the export errors with a
+missing `ai_edge_quantizer/recipes/` directory, create it empty — a packaging gap
+in some releases that trips the `.json`-recipe path.)
+
 ## License
 
 Falcon LLM License (TII), inherited from the base model