Update README.md

README.md

@@ -12,6 +12,8 @@ You can run this model on 8x H100 80GB using vLLM with
 
 `vllm serve adamo1139/DeepSeek-R1-0528-AWQ --tensor-parallel 8`
 
+If this doesn't work for you, you may need to manually specify quantization and datatype with `--quantization awq_marlin` and `--dtype float16` respectively.
+
 Script used for creating it is:
 
 ```