diff --git a/localai/localai-deployment.yaml b/localai/localai-deployment.yaml
new file mode 100644
index 0000000..9d82038
--- /dev/null
+++ b/localai/localai-deployment.yaml
@@ -0,0 +1,32 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: localai
+  namespace: localai-ns
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: localai
+  template:
+    metadata:
+      labels:
+        app: localai
+    spec:
+      runtimeClassName: nvidia
+      resources:
+        limits:
+          nvidia.com/gpu: 2
+      containers:
+      - name: localai
+        image: quay.io/go-skynet/local-ai:latest-aio-gpu-nvidia-cuda-12
+        ports:
+        - containerPort: 80
+        env:
+        volumeMounts:
+        - mountPath: "/models"
+          name: models
+      volumes:
+      - name: models
+        persistentVolumeClaim:
+          claimName: localai-pvc
diff --git a/localai/localai-helm-release.yaml b/localai/localai-helm-release.yaml.off
similarity index 100%
rename from localai/localai-helm-release.yaml
rename to localai/localai-helm-release.yaml.off
diff --git a/localai/localai-pvc.yaml b/localai/localai-pvc.yaml
new file mode 100644
index 0000000..81c8a6f
--- /dev/null
+++ b/localai/localai-pvc.yaml
@@ -0,0 +1,11 @@
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: localai-pvc
+  namespace: localai-ns
+spec:
+  accessModes:
+    - ReadWritemany
+  resources:
+    requests:
+      storage: 20Gi
diff --git a/localai/localai-service.yaml b/localai/localai-service.yaml
new file mode 100644
index 0000000..d10e413
--- /dev/null
+++ b/localai/localai-service.yaml
@@ -0,0 +1,13 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: localai
+  namespace: localai-ns
+spec:
+  type: LoadBalancer
+  selector:
+    app: localai
+  ports:
+  - port: 80
+    targetPort: 80
+    protocol: TCP