Add note clarifying HF param count vs actual 196.81B

README.md

@@ -12,17 +12,14 @@ tags:
 library_name: transformers
 quantized_by: tacos4me
 pipeline_tag: text-generation
-model-index:
-  - name: Step-3.5-Flash-NVFP4
-    results: []
-extra:
-  num_params: 196810000000
 ---
 
 # Step-3.5-Flash-NVFP4
 
 NVFP4-quantized version of [stepfun-ai/Step-3.5-Flash](https://huggingface.co/stepfun-ai/Step-3.5-Flash), an open-source frontier-level reasoning model by StepFun with 196.81B total parameters and ~11B active parameters per token.
 
+> **Note:** HuggingFace displays ~111B params because it counts packed FP4 tensor elements (2 weights per byte). The actual model has **196.81B parameters**, identical to the base model.
+
 ## Model Description
 
 [Step 3.5 Flash](https://huggingface.co/stepfun-ai/Step-3.5-Flash) is an open-source foundation model designed for frontier-level reasoning and agentic capabilities with exceptional efficiency. Key highlights from the base model: