Upload README.md with huggingface_hub

README.md

@@ -56,6 +56,14 @@ tokenizer needed by MLX-VLM.
 - `config.json` (with `quantization` + `quantization_config`), `generation_config.json`,
   `processor_config.json`, tokenizer files, and `chat_template.jinja`.
 
+## Model size vs HF parameter display
+
+This is a **~5.1B-parameter** model (2.3B effective), identical to the source
+SnowFox checkpoint. Hugging Face's model page reports ~1.2B because the 4-bit
+weights are stored as *packed* `uint32` words (8 values each) and HF counts each
+packed word as one parameter. The packed word count is a storage detail, not the
+parameter count.
+
 ## Verification performed
 
 The conversion host has no Apple-Silicon MLX runtime, so the quantized package