diff --git a/unsloth/kernels/utils.py b/unsloth/kernels/utils.py
index 0b13c04532..b1211ae345 100644
--- a/unsloth/kernels/utils.py
+++ b/unsloth/kernels/utils.py
@@ -86,6 +86,15 @@ def is_cdna():
     )
 
 
+@functools.lru_cache(1)
+def is_rdna():
+    """Detect RDNA consumer/workstation GPUs (RDNA3, RDNA3.5, RDNA4)."""
+    if not is_hip():
+        return False
+    arch = triton.runtime.driver.active.get_current_target().arch
+    return arch.startswith("gfx1") and not is_cdna()
+
+
 def calculate_settings(
     n: int,
 ) -> (
diff --git a/unsloth/models/loader.py b/unsloth/models/loader.py
index 711476b759..7bb2a24e00 100644
--- a/unsloth/models/loader.py
+++ b/unsloth/models/loader.py
@@ -1131,6 +1131,14 @@ class FastModel(FastBaseModel):
             # Set norms to float32 since anyways they get upcasted to float32
             # common in both gemma-3 and gemma-3n
             os.environ["UNSLOTH_HIGH_PRECISION_LAYERNORM"] = "1"
+            # ROCm/HIP: Gemma3 compiled forward produces NaN on RDNA GPUs
+            # (gfx1100, gfx1101, gfx1102, gfx1150, gfx1151, etc.).
+            # Disable torch.compile for model forward; loss compilation is fine.
+            # See https://github.com/unslothai/unsloth/issues/3385
+            from unsloth.kernels.utils import is_rdna
+
+            if is_rdna():
+                os.environ["UNSLOTH_COMPILE_DISABLE"] = "partial"
         # Cohere
         elif "cohere2" in model_types_all and transformers_version < Version(
             "4.50.0.dev0"