Update README.md

README.md

@@ -10,6 +10,18 @@ extra_gated_button_content: Acknowledge license
 base_model: google/gemma-3-4b-pt
 ---
 
+# BNB Quantization Config
+
+```py
+BitsAndBytesConfig(
+  load_in_4bit=True,
+  bnb_4bit_quant_type="nf4",
+  bnb_4bit_use_double_quant=True,
+  bnb_4bit_compute_dtype=torch.bfloat16,
+  bnb_4bit_quant_storage=torch.bfloat16,
+)
+```
+
 # Gemma 3 model card
 
 **Model Page**: [Gemma](https://ai.google.dev/gemma/docs/core)