Update README.md

README.md

@@ -221,7 +221,7 @@ oc apply -f qwen-inferenceservice.yaml
 curl https://<inference-service-name>-predictor-default.<domain>/v1/chat/completions
         -H "Content-Type: application/json" \
         -d '{
-    "model": "Llama-4-Maverick-17B-128E-Instruct-FP8",
+    "model": "llama-3-3-70b-instruct-quantized-w4a16",
     "stream": true,
     "stream_options": {
         "include_usage": true