diff --git a/vllm/transformers_utils/model_arch_config_convertor.py b/vllm/transformers_utils/model_arch_config_convertor.py
index 705f5207b3687..3caf86bfa40d2 100644
--- a/vllm/transformers_utils/model_arch_config_convertor.py
+++ b/vllm/transformers_utils/model_arch_config_convertor.py
@@ -150,12 +150,18 @@ class ModelArchConfigConvertorBase:
             producer_name = quant_cfg.get("producer", {}).get("name")
             if producer_name == "modelopt":
                 quant_algo = quant_cfg.get("quantization", {}).get("quant_algo")
-                if quant_algo == "FP8":
-                    quant_cfg["quant_method"] = "modelopt"
-                elif quant_algo == "NVFP4":
-                    quant_cfg["quant_method"] = "modelopt_fp4"
-                elif quant_algo is not None:
-                    raise ValueError(f"Unknown ModelOpt quant algo: {quant_algo}")
+                if quant_algo is not None:
+                    quant_algo_upper = str(quant_algo).upper()
+                    if quant_algo_upper in {
+                        "FP8",
+                        "FP8_PER_CHANNEL_PER_TOKEN",
+                        "FP8_PB_WO",
+                    }:
+                        quant_cfg["quant_method"] = "modelopt"
+                    elif quant_algo_upper == "NVFP4":
+                        quant_cfg["quant_method"] = "modelopt_fp4"
+                    else:
+                        raise ValueError(f"Unknown ModelOpt quant algo: {quant_algo}")
 
         if quant_cfg is not None:
             # Use the community standard 'quant_method'