diff --git a/test/unit/test_uop_symbolic.py b/test/unit/test_uop_symbolic.py
index 7d38180dee..b46dad7411 100644
--- a/test/unit/test_uop_symbolic.py
+++ b/test/unit/test_uop_symbolic.py
@@ -483,9 +483,7 @@ class TestSymbolic(unittest.TestCase):
     lidx2 = Variable("lidx2", 0, 3)
     alu0 = gidx2*640+gidx1*160+(gidx0//5)*2+lidx0*320+lidx1*10
     self.helper_test_variable((alu0+lidx2*2+1)//20, 0, 8192,
-                              ("((((((gidx0//5)+lidx2)//5)+lidx1)//2)+(((gidx2*32)+(gidx1*8))+(lidx0*16)))",
-                               "(((lidx1+((lidx2+(gidx0//5))//5))//2)+((gidx2*32)+((gidx1*8)+(lidx0*16))))",
-                               "((((gidx1*8)+(gidx2*32))+(lidx0*16))+((lidx1+((lidx2+(gidx0//5))//5))//2))"))
+                              ("((((gidx1*8)+(gidx2*32))+(lidx0*16))+(((lidx2+(gidx0//5))+(lidx1*5))//10))",))
 
   def test_sum_div_complex2(self):
     gidx0 = Variable("gidx0", 0, 7)
@@ -499,8 +497,8 @@ class TestSymbolic(unittest.TestCase):
     gidx0 = Variable("gidx0", 0, 7)
     lidx2 = Variable("lidx2", 0, 12)
     lidx3 = Variable("lidx3", 0, 1)
-    self.helper_test_variable((gidx0*4+lidx2*2+lidx3)//12, 0, 4, ("(((lidx2//2)+gidx0)//3)", "((gidx0+(lidx2//2))//3)"))
-    self.helper_test_variable((lidx2*2+gidx0*4+lidx3)//12, 0, 4, ("(((lidx2//2)+gidx0)//3)", "((gidx0+(lidx2//2))//3)"))
+    self.helper_test_variable((gidx0*4+lidx2*2+lidx3)//12, 0, 4, ("((lidx2+(gidx0*2))//6)"))
+    self.helper_test_variable((lidx2*2+gidx0*4+lidx3)//12, 0, 4, ("((lidx2+(gidx0*2))//6)"))
 
   def test_sum_mul_distribute(self):
     gidx0 = Variable("gidx0", 0, 7)
diff --git a/tinygrad/uop/symbolic.py b/tinygrad/uop/symbolic.py
index f20f6f6e00..1c4f43e0aa 100644
--- a/tinygrad/uop/symbolic.py
+++ b/tinygrad/uop/symbolic.py
@@ -202,7 +202,8 @@ def nest_div_by_smallest_factor(d: UOp, x: UOp, y: UOp) -> UOp|None:
   # TODO: there are better ways to pick `div`, this sometimes adds extra divisions
   # TODO: add same optimization for mod
   div = min([y.arg]+[abs(f) for f in factors if abs(f) > 1 and (c%f)==0])
-  if (1 < div < c) and (newxs:=(newx:=(x//div)).simplify()) is not newx and x.vmin>=0 and newx.vmin>=0: return newxs//(c//div)
+  if (1 < div < c) and (newxs:=fold_divmod_congruence(newx:=(x//div), x, y.const_like(div))) is not None and x.vmin>=0 and newx.vmin>=0:
+    return newxs//(c//div)
   return None
 
 def simplify_remainder(d: UOp, x: UOp, y: UOp) -> UOp|None: