diff --git a/docs/source/getting_started/distributions/self_hosted_distro/ollama.md b/docs/source/getting_started/distributions/self_hosted_distro/ollama.md
index 4baf0cf88..d1e9ea67a 100644
--- a/docs/source/getting_started/distributions/self_hosted_distro/ollama.md
+++ b/docs/source/getting_started/distributions/self_hosted_distro/ollama.md
@@ -60,9 +60,8 @@ docker run \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ~/.llama:/root/.llama \
   -v ./run.yaml:/root/my-run.yaml \
-  --gpus=all \
   llamastack/distribution-ollama \
-  /root/my-run.yaml \
+  --yaml-config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \
   --env INFERENCE_MODEL=$INFERENCE_MODEL \
   --env OLLAMA_URL=http://host.docker.internal:11434
@@ -76,9 +75,8 @@ docker run \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ~/.llama:/root/.llama \
   -v ./run-with-safety.yaml:/root/my-run.yaml \
-  --gpus=all \
   llamastack/distribution-ollama \
-  /root/my-run.yaml \
+  --yaml-config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \
   --env INFERENCE_MODEL=$INFERENCE_MODEL \
   --env SAFETY_MODEL=$SAFETY_MODEL \
diff --git a/llama_stack/templates/ollama/doc_template.md b/llama_stack/templates/ollama/doc_template.md
index 74a1866f9..5a7a0d2f7 100644
--- a/llama_stack/templates/ollama/doc_template.md
+++ b/llama_stack/templates/ollama/doc_template.md
@@ -56,9 +56,8 @@ docker run \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ~/.llama:/root/.llama \
   -v ./run.yaml:/root/my-run.yaml \
-  --gpus=all \
   llamastack/distribution-{{ name }} \
-  /root/my-run.yaml \
+  --yaml-config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \
   --env INFERENCE_MODEL=$INFERENCE_MODEL \
   --env OLLAMA_URL=http://host.docker.internal:11434
@@ -72,9 +71,8 @@ docker run \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ~/.llama:/root/.llama \
   -v ./run-with-safety.yaml:/root/my-run.yaml \
-  --gpus=all \
   llamastack/distribution-{{ name }} \
-  /root/my-run.yaml \
+  --yaml-config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \
   --env INFERENCE_MODEL=$INFERENCE_MODEL \
   --env SAFETY_MODEL=$SAFETY_MODEL \
diff --git a/llama_stack/templates/together/run.yaml b/llama_stack/templates/together/run.yaml
index bd28f0de3..855ba0626 100644
--- a/llama_stack/templates/together/run.yaml
+++ b/llama_stack/templates/together/run.yaml
@@ -78,7 +78,7 @@ models:
   provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
 shields:
 - params: null
-  shield_id: meta-llama/Llama-Guard-3-1B
+  shield_id: meta-llama/Llama-Guard-3-8B
   provider_id: null
   provider_shield_id: null
 memory_banks: []