Note: '8-bit precision' badge is HF reading uint8 packing — model is 4-bit MXFP4

README.md

@@ -116,6 +116,11 @@ modules to `quantization_config.ignore`** (else vLLM loads them as quantized →
 
 ## Caveats
 
+- **HF shows an "8-bit precision" badge — ignore it, this model is 4-bit.** MXFP4 packs two
+  4-bit FP4 values into each `uint8` byte (`weight_packed`), so HF reads the `uint8` *storage*
+  dtype and mislabels it. Source of truth: `config.json` → `num_bits: 4`,
+  `format: mxfp4-pack-quantized`. Every MXFP4 compressed-tensors model shows this (incl. the base).
+
 - Built/tested only on **gfx1201 (RDNA4)** with `tcclaviger/vllm-rocm-mxfp4-nvfp4`.
 - Reasons **inline in `content`** — the qwen3 reasoning-parser returns empty `reasoning_content`.
 - `--language-model-only` required (see Serving).