diff --git a/docs/source/distributions/self_hosted_distro/meta-reference-gpu.md b/docs/source/distributions/self_hosted_distro/meta-reference-gpu.md
index f532ce7ec..d46039318 100644
--- a/docs/source/distributions/self_hosted_distro/meta-reference-gpu.md
+++ b/docs/source/distributions/self_hosted_distro/meta-reference-gpu.md
@@ -63,7 +63,7 @@ docker run \
   -v ~/.llama:/root/.llama \
   llamastack/distribution-meta-reference-gpu \
   --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=Llama3.2-3B-Instruct
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
 ```
 
 If you are using Llama Stack Safety / Shield APIs, use:
@@ -75,8 +75,8 @@ docker run \
   -v ~/.llama:/root/.llama \
   llamastack/distribution-meta-reference-gpu \
   --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=Llama3.2-3B-Instruct \
-  --env SAFETY_MODEL=Llama-Guard-3-1B
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
+  --env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
 ```
 
 ### Via Conda
@@ -87,7 +87,7 @@ Make sure you have done `pip install llama-stack` and have the Llama Stack CLI a
 llama stack build --template meta-reference-gpu --image-type conda
 llama stack run distributions/meta-reference-gpu/run.yaml \
   --port 5001 \
-  --env INFERENCE_MODEL=Llama3.2-3B-Instruct
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
 ```
 
 If you are using Llama Stack Safety / Shield APIs, use:
@@ -95,6 +95,6 @@ If you are using Llama Stack Safety / Shield APIs, use:
 ```bash
 llama stack run distributions/meta-reference-gpu/run-with-safety.yaml \
   --port 5001 \
-  --env INFERENCE_MODEL=Llama3.2-3B-Instruct \
-  --env SAFETY_MODEL=Llama-Guard-3-1B
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
+  --env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
 ```
diff --git a/docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md b/docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md
index 23302a3ab..837be744a 100644
--- a/docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md
+++ b/docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md
@@ -33,7 +33,7 @@ Note that you need access to nvidia GPUs to run this distribution. This distribu
 The following environment variables can be configured:
 
 - `LLAMASTACK_PORT`: Port for the Llama Stack distribution server (default: `5001`)
-- `INFERENCE_MODEL`: Inference model loaded into the Meta Reference server (default: `Llama3.2-3B-Instruct`)
+- `INFERENCE_MODEL`: Inference model loaded into the Meta Reference server (default: `meta-llama/Llama-3.2-3B-Instruct`)
 - `INFERENCE_CHECKPOINT_DIR`: Directory containing the Meta Reference model checkpoint (default: `null`)
 
 
@@ -63,7 +63,7 @@ docker run \
   -v ~/.llama:/root/.llama \
   llamastack/distribution-meta-reference-quantized-gpu \
   --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=Llama3.2-3B-Instruct
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
 ```
 
 If you are using Llama Stack Safety / Shield APIs, use:
@@ -75,8 +75,8 @@ docker run \
   -v ~/.llama:/root/.llama \
   llamastack/distribution-meta-reference-quantized-gpu \
   --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=Llama3.2-3B-Instruct \
-  --env SAFETY_MODEL=Llama-Guard-3-1B
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
+  --env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
 ```
 
 ### Via Conda
@@ -87,7 +87,7 @@ Make sure you have done `pip install llama-stack` and have the Llama Stack CLI a
 llama stack build --template meta-reference-quantized-gpu --image-type conda
 llama stack run distributions/meta-reference-quantized-gpu/run.yaml \
   --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=Llama3.2-3B-Instruct
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
 ```
 
 If you are using Llama Stack Safety / Shield APIs, use:
@@ -95,6 +95,6 @@ If you are using Llama Stack Safety / Shield APIs, use:
 ```bash
 llama stack run distributions/meta-reference-quantized-gpu/run-with-safety.yaml \
   --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=Llama3.2-3B-Instruct \
-  --env SAFETY_MODEL=Llama-Guard-3-1B
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
+  --env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
 ```
diff --git a/llama_stack/templates/meta-reference-gpu/doc_template.md b/llama_stack/templates/meta-reference-gpu/doc_template.md
index 71653cfc1..421812dbc 100644
--- a/llama_stack/templates/meta-reference-gpu/doc_template.md
+++ b/llama_stack/templates/meta-reference-gpu/doc_template.md
@@ -53,7 +53,7 @@ docker run \
   -v ~/.llama:/root/.llama \
   llamastack/distribution-{{ name }} \
   --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=Llama3.2-3B-Instruct
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
 ```
 
 If you are using Llama Stack Safety / Shield APIs, use:
@@ -65,8 +65,8 @@ docker run \
   -v ~/.llama:/root/.llama \
   llamastack/distribution-{{ name }} \
   --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=Llama3.2-3B-Instruct \
-  --env SAFETY_MODEL=Llama-Guard-3-1B
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
+  --env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
 ```
 
 ### Via Conda
@@ -77,7 +77,7 @@ Make sure you have done `pip install llama-stack` and have the Llama Stack CLI a
 llama stack build --template {{ name }} --image-type conda
 llama stack run distributions/{{ name }}/run.yaml \
   --port 5001 \
-  --env INFERENCE_MODEL=Llama3.2-3B-Instruct
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
 ```
 
 If you are using Llama Stack Safety / Shield APIs, use:
@@ -85,6 +85,6 @@ If you are using Llama Stack Safety / Shield APIs, use:
 ```bash
 llama stack run distributions/{{ name }}/run-with-safety.yaml \
   --port 5001 \
-  --env INFERENCE_MODEL=Llama3.2-3B-Instruct \
-  --env SAFETY_MODEL=Llama-Guard-3-1B
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
+  --env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
 ```
diff --git a/llama_stack/templates/meta-reference-quantized-gpu/doc_template.md b/llama_stack/templates/meta-reference-quantized-gpu/doc_template.md
index 897a5faf7..daa380d20 100644
--- a/llama_stack/templates/meta-reference-quantized-gpu/doc_template.md
+++ b/llama_stack/templates/meta-reference-quantized-gpu/doc_template.md
@@ -55,7 +55,7 @@ docker run \
   -v ~/.llama:/root/.llama \
   llamastack/distribution-{{ name }} \
   --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=Llama3.2-3B-Instruct
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
 ```
 
 If you are using Llama Stack Safety / Shield APIs, use:
@@ -67,8 +67,8 @@ docker run \
   -v ~/.llama:/root/.llama \
   llamastack/distribution-{{ name }} \
   --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=Llama3.2-3B-Instruct \
-  --env SAFETY_MODEL=Llama-Guard-3-1B
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
+  --env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
 ```
 
 ### Via Conda
@@ -79,7 +79,7 @@ Make sure you have done `pip install llama-stack` and have the Llama Stack CLI a
 llama stack build --template {{ name }} --image-type conda
 llama stack run distributions/{{ name }}/run.yaml \
   --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=Llama3.2-3B-Instruct
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
 ```
 
 If you are using Llama Stack Safety / Shield APIs, use:
@@ -87,6 +87,6 @@ If you are using Llama Stack Safety / Shield APIs, use:
 ```bash
 llama stack run distributions/{{ name }}/run-with-safety.yaml \
   --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=Llama3.2-3B-Instruct \
-  --env SAFETY_MODEL=Llama-Guard-3-1B
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
+  --env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
 ```
diff --git a/llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py b/llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py
index 68d84ba67..c460860c5 100644
--- a/llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py
+++ b/llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py
@@ -84,7 +84,7 @@ def get_distribution_template() -> DistributionTemplate:
                 "Port for the Llama Stack distribution server",
             ),
             "INFERENCE_MODEL": (
-                "Llama3.2-3B-Instruct",
+                "meta-llama/Llama-3.2-3B-Instruct",
                 "Inference model loaded into the Meta Reference server",
             ),
             "INFERENCE_CHECKPOINT_DIR": (