diff --git a/comfy/model_management.py b/comfy/model_management.py
index 6f8c11c7f..3b10175f1 100644
--- a/comfy/model_management.py
+++ b/comfy/model_management.py
@@ -341,7 +341,7 @@ if ENABLE_PYTORCH_ATTENTION:
 
 PRIORITIZE_FP16 = False  # TODO: remove and replace with something that shows exactly which dtype is faster than the other
 try:
-    if is_nvidia() and PerformanceFeature.Fp16Accumulation in args.fast:
+    if (is_nvidia() or is_amd()) and PerformanceFeature.Fp16Accumulation in args.fast:
         torch.backends.cuda.matmul.allow_fp16_accumulation = True
         PRIORITIZE_FP16 = True  # TODO: limit to cards where it actually boosts performance
         logging.info("Enabled fp16 accumulation.")