diff --git a/modules/sdnq/common.py b/modules/sdnq/common.py
index ed131423d..5bcd60ce9 100644
--- a/modules/sdnq/common.py
+++ b/modules/sdnq/common.py
@@ -44,7 +44,7 @@ if os.environ.get("SDNQ_USE_TENSORWISE_FP8_MM", None) is None:
     # row-wise FP8 only exist on H100 hardware, sdnq will use software row-wise with tensorwise hardware with this setting
     use_tensorwise_fp8_matmul = bool(devices.backend == "cuda" and torch.cuda.get_device_capability(devices.device) < (9,0))
 else:
-    use_tensorwise_fp8_matmul = os.environ.get("SDNQ_USE_TENSORWISE_FP8_MM", "1").lower() not in {"0", "false", "no"}
+    use_tensorwise_fp8_matmul = os.environ.get("SDNQ_USE_TENSORWISE_FP8_MM", "0").lower() not in {"0", "false", "no"}
 
 if os.environ.get("SDNQ_USE_CONTIGUOUS_MM", None) is None:
     use_contiguous_mm = bool(is_rdna2 or devices.backend in {"cpu", "ipex", "zluda"})