diff --git a/comfy/cli_args.py b/comfy/cli_args.py
index dae9a895d..345147317 100644
--- a/comfy/cli_args.py
+++ b/comfy/cli_args.py
@@ -151,6 +151,7 @@ parser.add_argument("--force-non-blocking", action="store_true", help="Force Com
 
 parser.add_argument("--default-hashing-function", type=str, choices=['md5', 'sha1', 'sha256', 'sha512'], default='sha256', help="Allows you to choose the hash function to use for duplicate filename / contents comparison. Default is sha256.")
 
+parser.add_argument("--disable-fp8-compute", action="store_true", help="Prevent ComfyUI from activating fp8 compute in Nvidia cards that support it. Can prevent some issues with some models not suitable for fp8 compute.")
 parser.add_argument("--disable-smart-memory", action="store_true", help="Force ComfyUI to agressively offload to regular ram instead of keeping models in vram when it can.")
 parser.add_argument("--deterministic", action="store_true", help="Make pytorch use slower deterministic algorithms when it can. Note that this might not make images deterministic in all cases.")
 
diff --git a/comfy/model_management.py b/comfy/model_management.py
index 928282092..ee961d844 100644
--- a/comfy/model_management.py
+++ b/comfy/model_management.py
@@ -1486,6 +1486,8 @@ def supports_fp8_compute(device=None):
 
     if not is_nvidia():
         return False
+    if args.disable_fp8_compute:
+        return False
 
     props = torch.cuda.get_device_properties(device)
     if props.major >= 9: