diff --git a/docs/docs/examples/multi_modal/nvidia_multi_modal.ipynb b/docs/docs/examples/multi_modal/nvidia_multi_modal.ipynb
index 5753e690097f0..17c1434f31214 100644
--- a/docs/docs/examples/multi_modal/nvidia_multi_modal.ipynb
+++ b/docs/docs/examples/multi_modal/nvidia_multi_modal.ipynb
@@ -74,6 +74,16 @@
     "llm = NVIDIAMultiModal()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## To get available models use available_models property\n",
+    "llm.available_models"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -482,8 +492,7 @@
     "    [\n",
     "        ChatMessage(\n",
     "            role=\"user\",\n",
-    "            content=f\"\"\"<img src=\"data:image/jpg;\n",
-    "            ,{asset_id}\"/>\"\"\",\n",
+    "            content=f\"\"\"Describe the Image: <img src=\"data:image/jpg;asset_id,{asset_id}\"/>\"\"\",\n",
     "        )\n",
     "    ]\n",
     ")"
diff --git a/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/llama_index/multi_modal_llms/nvidia/base.py b/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/llama_index/multi_modal_llms/nvidia/base.py
index e14dfa616f510..bd8eabe05f889 100644
--- a/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/llama_index/multi_modal_llms/nvidia/base.py
+++ b/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/llama_index/multi_modal_llms/nvidia/base.py
@@ -30,6 +30,7 @@
 
 from llama_index.multi_modal_llms.nvidia.utils import (
     BASE_URL,
+    DEFAULT_MODEL,
     KNOWN_URLS,
     NVIDIA_MULTI_MODAL_MODELS,
     generate_nvidia_multi_modal_chat_message,
@@ -38,6 +39,7 @@
 )
 import aiohttp
 import json
+import warnings
 
 from llama_index.core.bridge.pydantic import BaseModel
 
@@ -154,7 +156,7 @@ class NVIDIAMultiModal(MultiModalLLM):
 
     def __init__(
         self,
-        model: str = "microsoft/phi-3-vision-128k-instruct",
+        model: str = None,
         temperature: float = DEFAULT_TEMPERATURE,
         max_tokens: Optional[int] = 300,
         nvidia_api_key: Optional[str] = None,
@@ -177,6 +179,16 @@ def __init__(
                 "An API key is required for the hosted NIM. This will become an error in 0.2.0."
             )
 
+        ## set default model
+        if not model:
+            model = DEFAULT_MODEL
+            warnings.warn(
+                f"Default model is set as: {model}. \n"
+                "Set model using model parameter. \n"
+                "To get available models use available_models property.",
+                UserWarning,
+            )
+
         super().__init__(
             model=model,
             temperature=temperature,
diff --git a/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/llama_index/multi_modal_llms/nvidia/utils.py b/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/llama_index/multi_modal_llms/nvidia/utils.py
index fa4d00bcd2a65..7401238bc9512 100644
--- a/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/llama_index/multi_modal_llms/nvidia/utils.py
+++ b/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/llama_index/multi_modal_llms/nvidia/utils.py
@@ -8,7 +8,7 @@
 import urllib
 from llama_index.core.base.llms.types import ChatMessage
 
-DEFAULT_MODEL = "microsoft/phi-3-vision-128k-instruct"
+DEFAULT_MODEL = "nvidia/neva-22b"
 BASE_URL = "https://ai.api.nvidia.com/v1/"
 
 KNOWN_URLS = [
diff --git a/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/pyproject.toml b/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/pyproject.toml
index 7ddbfba1c7a4b..019199e1620fa 100644
--- a/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/pyproject.toml
+++ b/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/pyproject.toml
@@ -30,7 +30,7 @@ license = "MIT"
 name = "llama-index-multi-modal-llms-nvidia"
 packages = [{include = "llama_index/"}]
 readme = "README.md"
-version = "0.3.0"
+version = "0.3.1"
 
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"
diff --git a/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/tests/test_multi_modal_nvidia.py b/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/tests/test_multi_modal_nvidia.py
index afe97b2d210c3..e4387884990bc 100644
--- a/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/tests/test_multi_modal_nvidia.py
+++ b/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/tests/test_multi_modal_nvidia.py
@@ -2,6 +2,7 @@
 from llama_index.multi_modal_llms.nvidia import NVIDIAMultiModal
 from llama_index.multi_modal_llms.nvidia.utils import (
     NVIDIA_MULTI_MODAL_MODELS,
+    DEFAULT_MODEL,
 )
 import base64
 import os
@@ -434,3 +435,15 @@ async def test_vlm_chat_async_stream(vlm_model: str) -> None:
     async for token in await llm.astream_chat(messages):
         assert isinstance(token, ChatResponse)
         assert isinstance(token.delta, str)
+
+
+def test_default_known() -> None:
+    """
+    Test that a model in the model table will be accepted.
+    """
+    # check if default model is getting set
+    with pytest.warns(UserWarning) as record:
+        x = NVIDIAMultiModal()
+        assert x.model == DEFAULT_MODEL
+    assert len(record) == 1
+    assert f"Default model is set as: {DEFAULT_MODEL}" in str(record[0].message)