diff --git a/localai/local-ai-deployment.yaml b/localai/local-ai-deployment.yaml
deleted file mode 100644
index 2a7b90c..0000000
--- a/localai/local-ai-deployment.yaml
+++ /dev/null
@@ -1,37 +0,0 @@
-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:v2.14.0-cublas-cuda12
-          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-service.yaml b/localai/local-ai-service.yaml
deleted file mode 100644
index b86c80d..0000000
--- a/localai/local-ai-service.yaml
+++ /dev/null
@@ -1,13 +0,0 @@
-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
diff --git a/ollama/ollama-deployment.yaml b/ollama/ollama-deployment.yaml
new file mode 100644
index 0000000..ffb33e4
--- /dev/null
+++ b/ollama/ollama-deployment.yaml
@@ -0,0 +1,36 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: ollama-deployment
+  namespace: ollama-ns
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: ollama
+  template:
+    metadata:
+      labels:
+        app: ollama
+    spec:
+      runtimeClassName: nvidia
+      containers:
+      - name: ollama
+        image: ollama/ollama
+        env:
+        - name: OLLAMA_HOST
+          value: 0.0.0.0
+        - name: OLLAMA_MODELS
+          value: "/models"
+        ports:
+        - containerPort: 11434
+        resources:
+          limits:
+            nvidia.com/gpu: 2
+        volumeMounts:
+        - name: ollama-volume
+          mountPath: "/my-models"
+      volumes:
+      - name: ollama-volume
+        persistentVolumeClaim:
+          claimName: ollama-pvc
diff --git a/localai/local-ai-pvc.yaml b/ollama/ollama-pvc.yaml
similarity index 60%
rename from localai/local-ai-pvc.yaml
rename to ollama/ollama-pvc.yaml
index ca00a7a..f2d2aa0 100644
--- a/localai/local-ai-pvc.yaml
+++ b/ollama/ollama-pvc.yaml
@@ -1,12 +1,12 @@
 apiVersion: v1
 kind: PersistentVolumeClaim
 metadata:
-  name: models-pvc
-  namespace: local-ai-ns
+  name: ollama-pvc
+  namespace: ollama-ns
 spec:
   accessModes:
-    - ReadWriteMany
+    - ReadWriteOnce
   storageClassName: longhorn
   resources:
     requests:
-      storage: 100Gi
+      storage: 200Gi
diff --git a/ollama/ollama-service.yaml b/ollama/ollama-service.yaml
new file mode 100644
index 0000000..d034c21
--- /dev/null
+++ b/ollama/ollama-service.yaml
@@ -0,0 +1,12 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: ollama-service
+  namespace: ollama-ns
+spec:
+  type: LoadBalancer
+  ports:
+  - port: 11434
+    targetPort: 11434
+  selector:
+    app: ollama