diff --git a/distributions/inline-nvidia/build.yaml b/distributions/inline-nvidia/build.yaml
new file mode 120000
index 0000000000..8903d2e572
--- /dev/null
+++ b/distributions/inline-nvidia/build.yaml
@@ -0,0 +1 @@
+../../llama_stack/templates/nvidia/build.yaml
\ No newline at end of file
diff --git a/distributions/inline-nvidia/compose.yaml b/distributions/inline-nvidia/compose.yaml
new file mode 100644
index 0000000000..f7320b9686
--- /dev/null
+++ b/distributions/inline-nvidia/compose.yaml
@@ -0,0 +1,58 @@
+services:
+  nim:
+    image: nvcr.io/nim/meta/llama-3.1-8b-instruct:latest
+    network_mode: "host"
+    volumes:
+    - nim-llm-cache:/opt/nim/.cache
+    ports:
+      - "8000:8000"
+    shm_size: 16G
+    environment:
+      - CUDA_VISIBLE_DEVICES=0
+      - NIM_HTTP_API_PORT=8000
+      - NIM_TRITON_LOG_VERBOSE=1
+      - NGC_API_KEY=${NIM_NGC_API_KEY:-${NGC_API_KEY:-ngcapikey}}
+    command: []
+    deploy:
+      resources:
+        reservations:
+          devices:
+          - driver: nvidia
+            # that's the closest analogue to --gpus; provide
+            # an integer amount of devices or 'all'
+            count: 1
+            # Devices are reserved using a list of capabilities, making
+            # capabilities the only required field. A device MUST
+            # satisfy all the requested capabilities for a successful
+            # reservation.
+            capabilities: [gpu]
+    runtime: nvidia
+    healthcheck:
+      test: ["CMD", "curl", "http://localhost:8000/v1/health/ready"]
+      interval: 5s
+      timeout: 5s
+      retries: 30
+      start_period: 120s
+  llamastack:
+    depends_on:
+    - nim
+    image: distribution-nvidia:dev
+    network_mode: "host"
+    volumes:
+      - ~/.llama:/root/.llama
+      - ./run.yaml:/root/llamastack-run-nvidia.yaml
+    ports:
+      - "5000:5000"
+    environment:
+      - INFERENCE_MODEL=${INFERENCE_MODEL:-Llama3.1-8B-Instruct}
+      - NVIDIA_API_KEY=${NVIDIA_API_KEY:-}
+    entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml-config /root/llamastack-run-nvidia.yaml"
+    deploy:
+      restart_policy:
+        condition: on-failure
+        delay: 3s
+        max_attempts: 5
+        window: 60s
+volumes:
+  nim-llm-cache:
+    driver: local
\ No newline at end of file
diff --git a/distributions/inline-nvidia/run.yaml b/distributions/inline-nvidia/run.yaml
new file mode 100644
index 0000000000..81e9e7f1c0
--- /dev/null
+++ b/distributions/inline-nvidia/run.yaml
@@ -0,0 +1,56 @@
+version: '2'
+image_name: nvidia
+docker_image: null
+conda_env: nvidia
+apis:
+- agents
+- inference
+- memory
+- safety
+- telemetry
+providers:
+  inference:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      url: http://localhost:8000
+      api_key: ${env.NVIDIA_API_KEY}
+  memory:
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/faiss_store.db
+  safety:
+  - provider_id: llama-guard
+    provider_type: inline::llama-guard
+    config: {}
+  agents:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      persistence_store:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/agents_store.db
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config: {}
+metadata_store:
+  namespace: null
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db
+models:
+- metadata: {}
+  model_id: ${env.INFERENCE_MODEL}
+  provider_id: nvidia
+  provider_model_id: null
+shields: []
+memory_banks: []
+datasets: []
+scoring_fns: []
+eval_tasks: []
+
diff --git a/distributions/remote-nvidia/build.yaml b/distributions/remote-nvidia/build.yaml
new file mode 120000
index 0000000000..8903d2e572
--- /dev/null
+++ b/distributions/remote-nvidia/build.yaml
@@ -0,0 +1 @@
+../../llama_stack/templates/nvidia/build.yaml
\ No newline at end of file
diff --git a/distributions/remote-nvidia/compose.yaml b/distributions/remote-nvidia/compose.yaml
new file mode 100644
index 0000000000..04b12d0da2
--- /dev/null
+++ b/distributions/remote-nvidia/compose.yaml
@@ -0,0 +1,19 @@
+services:
+  llamastack:
+    image: distribution-nvidia:dev
+    network_mode: "host"
+    volumes:
+      - ~/.llama:/root/.llama
+      - ./run.yaml:/root/llamastack-run-nvidia.yaml
+    ports:
+      - "5000:5000"
+    environment:
+      - INFERENCE_MODEL=${INFERENCE_MODEL:-Llama3.1-8B-Instruct}
+      - NVIDIA_API_KEY=${NVIDIA_API_KEY:-}
+    entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml-config /root/llamastack-run-nvidia.yaml"
+    deploy:
+      restart_policy:
+        condition: on-failure
+        delay: 3s
+        max_attempts: 5
+        window: 60s
diff --git a/distributions/remote-nvidia/run.yaml b/distributions/remote-nvidia/run.yaml
new file mode 120000
index 0000000000..85da3e26bd
--- /dev/null
+++ b/distributions/remote-nvidia/run.yaml
@@ -0,0 +1 @@
+../../llama_stack/templates/nvidia/run.yaml
\ No newline at end of file
diff --git a/docs/source/distributions/index.md b/docs/source/distributions/index.md
index b61e9b28f5..e88960a848 100644
--- a/docs/source/distributions/index.md
+++ b/docs/source/distributions/index.md
@@ -24,6 +24,7 @@ If so, we suggest:
   - {dockerhub}`distribution-remote-vllm` ([Guide](self_hosted_distro/remote-vllm))
   - {dockerhub}`distribution-meta-reference-gpu` ([Guide](self_hosted_distro/meta-reference-gpu))
   - {dockerhub}`distribution-tgi` ([Guide](self_hosted_distro/tgi))
+  - {dockerhub} `distribution-nvidia` ([Guide](self_hosted_distro/nvidia))
 
 - **Are you running on a "regular" desktop machine?**
 If so, we suggest:
diff --git a/docs/source/distributions/self_hosted_distro/nvidia.md b/docs/source/distributions/self_hosted_distro/nvidia.md
new file mode 100644
index 0000000000..2f34997166
--- /dev/null
+++ b/docs/source/distributions/self_hosted_distro/nvidia.md
@@ -0,0 +1,60 @@
+# NVIDIA Distribution
+
+The `llamastack/distribution-nvidia` distribution consists of the following provider configurations.
+
+| API | Provider(s) |
+|-----|-------------|
+| agents | `inline::meta-reference` |
+| inference | `remote::nvidia` |
+| memory | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
+| safety | `inline::llama-guard` |
+| telemetry | `inline::meta-reference` |
+
+
+### Environment Variables
+
+The following environment variables can be configured:
+
+- `LLAMASTACK_PORT`: Port for the Llama Stack distribution server (default: `5001`)
+- `NVIDIA_API_KEY`: NVIDIA API Key (default: ``)
+
+### Models
+
+The following models are available by default:
+
+- `${env.INFERENCE_MODEL} (None)`
+
+
+### Prerequisite: API Keys
+
+Make sure you have access to a NVIDIA API Key. You can get one by visiting [https://build.nvidia.com/](https://build.nvidia.com/).
+
+
+## Running Llama Stack with NVIDIA
+
+You can do this via Conda (build code) or Docker which has a pre-built image.
+
+### Via Docker
+
+This method allows you to get started quickly without having to build the distribution code.
+
+```bash
+LLAMA_STACK_PORT=5001
+docker run \
+  -it \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v ./run.yaml:/root/my-run.yaml \
+  llamastack/distribution-nvidia \
+  --yaml-config /root/my-run.yaml \
+  --port $LLAMA_STACK_PORT \
+  --env NVIDIA_API_KEY=$NVIDIA_API_KEY
+```
+
+### Via Conda
+
+```bash
+llama stack build --template nvidia --image-type conda
+llama stack run ./run.yaml \
+  --port 5001 \
+  --env NVIDIA_API_KEY=$NVIDIA_API_KEY
+```
\ No newline at end of file
diff --git a/llama_stack/templates/nvidia/__init__.py b/llama_stack/templates/nvidia/__init__.py
new file mode 100644
index 0000000000..24e2fbd216
--- /dev/null
+++ b/llama_stack/templates/nvidia/__init__.py
@@ -0,0 +1,7 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from .nvidia import get_distribution_template  # noqa: F401
diff --git a/llama_stack/templates/nvidia/build.yaml b/llama_stack/templates/nvidia/build.yaml
new file mode 100644
index 0000000000..9a735c2203
--- /dev/null
+++ b/llama_stack/templates/nvidia/build.yaml
@@ -0,0 +1,19 @@
+version: '2'
+name: nvidia
+distribution_spec:
+  description: Use NVIDIA NIM for running LLM inference
+  docker_image: null
+  providers:
+    inference:
+    - remote::nvidia
+    memory:
+    - inline::faiss
+    - remote::chromadb
+    - remote::pgvector
+    safety:
+    - inline::llama-guard
+    agents:
+    - inline::meta-reference
+    telemetry:
+    - inline::meta-reference
+image_type: conda
diff --git a/llama_stack/templates/nvidia/doc_template.md b/llama_stack/templates/nvidia/doc_template.md
new file mode 100644
index 0000000000..949018f8d6
--- /dev/null
+++ b/llama_stack/templates/nvidia/doc_template.md
@@ -0,0 +1,60 @@
+# NVIDIA Distribution
+
+The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations.
+
+{{ providers_table }}
+
+{% if run_config_env_vars %}
+### Environment Variables
+
+The following environment variables can be configured:
+
+{% for var, (default_value, description) in run_config_env_vars.items() %}
+- `{{ var }}`: {{ description }} (default: `{{ default_value }}`)
+{% endfor %}
+{% endif %}
+
+{% if default_models %}
+### Models
+
+The following models are available by default:
+
+{% for model in default_models %}
+- `{{ model.model_id }} ({{ model.provider_model_id }})`
+{% endfor %}
+{% endif %}
+
+
+### Prerequisite: API Keys
+
+Make sure you have access to a NVIDIA API Key. You can get one by visiting [https://build.nvidia.com/](https://build.nvidia.com/).
+
+
+## Running Llama Stack with NVIDIA
+
+You can do this via Conda (build code) or Docker which has a pre-built image.
+
+### Via Docker
+
+This method allows you to get started quickly without having to build the distribution code.
+
+```bash
+LLAMA_STACK_PORT=5001
+docker run \
+  -it \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v ./run.yaml:/root/my-run.yaml \
+  llamastack/distribution-{{ name }} \
+  --yaml-config /root/my-run.yaml \
+  --port $LLAMA_STACK_PORT \
+  --env NVIDIA_API_KEY=$NVIDIA_API_KEY
+```
+
+### Via Conda
+
+```bash
+llama stack build --template nvidia --image-type conda
+llama stack run ./run.yaml \
+  --port 5001 \
+  --env NVIDIA_API_KEY=$NVIDIA_API_KEY
+```
diff --git a/llama_stack/templates/nvidia/nvidia.py b/llama_stack/templates/nvidia/nvidia.py
new file mode 100644
index 0000000000..22aa1f4b08
--- /dev/null
+++ b/llama_stack/templates/nvidia/nvidia.py
@@ -0,0 +1,62 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from pathlib import Path
+
+from llama_stack.distribution.datatypes import ModelInput, Provider
+from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
+from llama_stack.providers.remote.inference.nvidia.nvidia import _MODEL_ALIASES
+
+from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
+
+
+def get_distribution_template() -> DistributionTemplate:
+    providers = {
+        "inference": ["remote::nvidia"],
+        "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "safety": ["inline::llama-guard"],
+        "agents": ["inline::meta-reference"],
+        "telemetry": ["inline::meta-reference"],
+    }
+
+    inference_provider = Provider(
+        provider_id="nvidia",
+        provider_type="remote::nvidia",
+        config=NVIDIAConfig.sample_run_config(),
+    )
+
+    inference_model = ModelInput(
+        model_id="${env.INFERENCE_MODEL}",
+        provider_id="nvidia",
+    )
+
+    return DistributionTemplate(
+        name="nvidia",
+        distro_type="remote_hosted",
+        description="Use NVIDIA NIM for running LLM inference",
+        docker_image=None,
+        template_path=Path(__file__).parent / "doc_template.md",
+        providers=providers,
+        default_models=[inference_model],
+        run_configs={
+            "run.yaml": RunConfigSettings(
+                provider_overrides={
+                    "inference": [inference_provider],
+                },
+                default_models=[inference_model],
+            ),
+        },
+        run_config_env_vars={
+            "LLAMASTACK_PORT": (
+                "5001",
+                "Port for the Llama Stack distribution server",
+            ),
+            "NVIDIA_API_KEY": (
+                "",
+                "NVIDIA API Key",
+            ),
+        },
+    )
diff --git a/llama_stack/templates/nvidia/run.yaml b/llama_stack/templates/nvidia/run.yaml
new file mode 100644
index 0000000000..f4953852f5
--- /dev/null
+++ b/llama_stack/templates/nvidia/run.yaml
@@ -0,0 +1,55 @@
+version: '2'
+image_name: nvidia
+docker_image: null
+conda_env: nvidia
+apis:
+- agents
+- inference
+- memory
+- safety
+- telemetry
+providers:
+  inference:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      url: https://integrate.api.nvidia.com
+      api_key: ${env.NVIDIA_API_KEY}
+  memory:
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/faiss_store.db
+  safety:
+  - provider_id: llama-guard
+    provider_type: inline::llama-guard
+    config: {}
+  agents:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      persistence_store:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/agents_store.db
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config: {}
+metadata_store:
+  namespace: null
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db
+models:
+- metadata: {}
+  model_id: ${env.INFERENCE_MODEL}
+  provider_id: nvidia
+  provider_model_id: null
+shields: []
+memory_banks: []
+datasets: []
+scoring_fns: []
+eval_tasks: []