diff --git a/localai/local-ai-deployment.yaml b/localai/local-ai-deployment.yaml
new file mode 100644
index 0000000..795daa1
--- /dev/null
+++ b/localai/local-ai-deployment.yaml
@@ -0,0 +1,37 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: local-ai
+  namespace: local-ai-ns
+  labels:
+    app: local-ai
+spec:
+  selector:
+    matchLabels:
+      app: local-ai
+  replicas: 1
+  template:
+    metadata:
+      labels:
+        app: local-ai
+      name: local-ai
+    spec:
+      containers:
+        - args:
+          - dolphin-2.5-mixtral-8x7b
+          env:
+          - name: DEBUG
+            value: "true"
+          name: local-ai
+          image: quay.io/go-skynet/local-ai:master-ffmpeg-core
+          imagePullPolicy: IfNotPresent
+          resources:
+            limits:
+              nvidia.com/gpu: 2
+          volumeMounts:
+            - name: models-volume
+              mountPath: /build/models
+      volumes:
+        - name: models-volume
+          persistentVolumeClaim:
+            claimName: models-pvc
diff --git a/localai/local-ai-pvc.yaml b/localai/local-ai-pvc.yaml
new file mode 100644
index 0000000..ca00a7a
--- /dev/null
+++ b/localai/local-ai-pvc.yaml
@@ -0,0 +1,12 @@
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: models-pvc
+  namespace: local-ai-ns
+spec:
+  accessModes:
+    - ReadWriteMany
+  storageClassName: longhorn
+  resources:
+    requests:
+      storage: 100Gi
diff --git a/localai/local-ai-service.yaml b/localai/local-ai-service.yaml
new file mode 100644
index 0000000..b86c80d
--- /dev/null
+++ b/localai/local-ai-service.yaml
@@ -0,0 +1,13 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: local-ai
+  namespace: local-ai-ns
+spec:
+  selector:
+    app: local-ai
+  type: LoadBalancer
+  ports:
+    - protocol: TCP
+      port: 80
+      targetPort: 8080