Update README.md

README.md

@@ -86,7 +86,7 @@ This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/
 from vllm import LLM, SamplingParams
 from transformers import AutoProcessor
 
-model_id = "RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-FP8-dynamic"
+model_id = "RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8"
 number_gpus = 1
 
 sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)