diff --git a/tests/test_models.py b/tests/test_models.py
index de6640688f9ec7638701ae06d3c3e847bc401734..44cb3ba2e297f05b0e784b00112a87ecebd9dc91 100644
--- a/tests/test_models.py
+++ b/tests/test_models.py
@@ -190,7 +190,7 @@ EXCLUDE_JIT_FILTERS = [
 def test_model_forward_torchscript(model_name, batch_size):
     """Run a single forward pass with each model"""
     input_size = _get_input_size(model_name=model_name, target=TARGET_JIT_SIZE)
-    if max(input_size) > MAX_JIT_SIZE:  # NOTE using MAX_FWD_SIZE as the final limit is intentional
+    if max(input_size) > MAX_JIT_SIZE:
         pytest.skip("Fixed input size model > limit.")
 
     with set_scriptable(True):
diff --git a/timm/models/visformer.py b/timm/models/visformer.py
index 936f1ddf561c7a2f01a4d86e220309c04689ad71..33a2fe872a41326b16657db27995a8b550ffa71d 100644
--- a/timm/models/visformer.py
+++ b/timm/models/visformer.py
@@ -26,7 +26,7 @@ def _cfg(url='', **kwargs):
         'num_classes': 1000, 'input_size': (3, 224, 224), 'pool_size': None,
         'crop_pct': .9, 'interpolation': 'bicubic', 'fixed_input_size': True,
         'mean': IMAGENET_DEFAULT_MEAN, 'std': IMAGENET_DEFAULT_STD,
-        'first_conv': 'patch_embed.proj', 'classifier': 'head',
+        'first_conv': 'stem.0', 'classifier': 'head',
         **kwargs
     }
 
@@ -183,7 +183,7 @@ class Visformer(nn.Module):
                 img_size //= 8
             else:
                 self.stem = nn.Sequential(
-                    nn.Conv2d(3, self.init_channels, 7, stride=2, padding=3, bias=False),
+                    nn.Conv2d(in_chans, self.init_channels, 7, stride=2, padding=3, bias=False),
                     nn.BatchNorm2d(self.init_channels),
                     nn.ReLU(inplace=True)
                 )