Update README.md

README.md

@@ -7,4 +7,4 @@ This is a MXFP4_MOE quantization of the model Qwen3-Coder-REAP-246B-A35B
 
 Original model: https://huggingface.co/cerebras/Qwen3-Coder-REAP-246B-A35B-FP8
 
-As the original repository was already at FP8, I cannot guarantee any quality loss. I've tried to upscale it to F32 before quantizing it to MXFP4.
+The model was originally in FP8, which limits its precision. I attempted to apply MXFP4 quantization after converting the model to FP32, but the quality degradation from the initial FP8 quantization cannot be fully reversed.