diff --git a/llama_stack/providers/tests/README.md b/llama_stack/providers/tests/README.md
index 90b41a631..4b406b321 100644
--- a/llama_stack/providers/tests/README.md
+++ b/llama_stack/providers/tests/README.md
@@ -44,7 +44,7 @@ Finally, you can override the model completely by doing:
 ```bash
 pytest -s -v llama_stack/providers/tests/inference/test_text_inference.py \
   -m fireworks \
-  --inference-model "Llama3.1-70B-Instruct" \
+  --inference-model "meta-llama/Llama3.1-70B-Instruct" \
   --env FIREWORKS_API_KEY=<...>
 ```
 
diff --git a/llama_stack/providers/tests/agents/conftest.py b/llama_stack/providers/tests/agents/conftest.py
index 6ce7913d7..7d8d4d089 100644
--- a/llama_stack/providers/tests/agents/conftest.py
+++ b/llama_stack/providers/tests/agents/conftest.py
@@ -81,13 +81,13 @@ def pytest_addoption(parser):
     parser.addoption(
         "--inference-model",
         action="store",
-        default="Llama3.1-8B-Instruct",
+        default="meta-llama/Llama-3.1-8B-Instruct",
         help="Specify the inference model to use for testing",
     )
     parser.addoption(
         "--safety-shield",
         action="store",
-        default="Llama-Guard-3-8B",
+        default="meta-llama/Llama-Guard-3-8B",
         help="Specify the safety shield to use for testing",
     )
 
diff --git a/llama_stack/providers/tests/eval/conftest.py b/llama_stack/providers/tests/eval/conftest.py
index caf7f0290..171fae51a 100644
--- a/llama_stack/providers/tests/eval/conftest.py
+++ b/llama_stack/providers/tests/eval/conftest.py
@@ -63,7 +63,7 @@ def pytest_addoption(parser):
     parser.addoption(
         "--inference-model",
         action="store",
-        default="Llama3.2-3B-Instruct",
+        default="meta-llama/Llama-3.2-3B-Instruct",
         help="Specify the inference model to use for testing",
     )
 
diff --git a/llama_stack/providers/tests/inference/conftest.py b/llama_stack/providers/tests/inference/conftest.py
index ba60b9925..d013d6a9e 100644
--- a/llama_stack/providers/tests/inference/conftest.py
+++ b/llama_stack/providers/tests/inference/conftest.py
@@ -32,8 +32,12 @@ def pytest_configure(config):
 
 
 MODEL_PARAMS = [
-    pytest.param("Llama3.1-8B-Instruct", marks=pytest.mark.llama_8b, id="llama_8b"),
-    pytest.param("Llama3.2-3B-Instruct", marks=pytest.mark.llama_3b, id="llama_3b"),
+    pytest.param(
+        "meta-llama/Llama-3.1-8B-Instruct", marks=pytest.mark.llama_8b, id="llama_8b"
+    ),
+    pytest.param(
+        "meta-llama/Llama-3.2-3B-Instruct", marks=pytest.mark.llama_3b, id="llama_3b"
+    ),
 ]
 
 VISION_MODEL_PARAMS = [
diff --git a/llama_stack/providers/tests/scoring/conftest.py b/llama_stack/providers/tests/scoring/conftest.py
index e8ecfaa68..327acab84 100644
--- a/llama_stack/providers/tests/scoring/conftest.py
+++ b/llama_stack/providers/tests/scoring/conftest.py
@@ -58,7 +58,7 @@ def pytest_addoption(parser):
     parser.addoption(
         "--inference-model",
         action="store",
-        default="Llama3.2-3B-Instruct",
+        default="meta-llama/Llama-3.2-3B-Instruct",
         help="Specify the inference model to use for testing",
     )