diff --git a/swagger/docs.go b/swagger/docs.go
index b7f5617a5..f1f3f8ae9 100644
--- a/swagger/docs.go
+++ b/swagger/docs.go
@@ -907,6 +907,90 @@ const docTemplate = `{
                 }
             }
         },
+        "/api/nodes/{id}/max-replicas-per-model": {
+            "put": {
+                "tags": [
+                    "Nodes"
+                ],
+                "summary": "Update a node's max replicas per model",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Node ID",
+                        "name": "id",
+                        "in": "path",
+                        "required": true
+                    },
+                    {
+                        "description": "New value",
+                        "name": "request",
+                        "in": "body",
+                        "required": true,
+                        "schema": {
+                            "$ref": "#/definitions/localai.UpdateMaxReplicasPerModelRequest"
+                        }
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "OK",
+                        "schema": {
+                            "type": "object",
+                            "additionalProperties": {
+                                "type": "integer"
+                            }
+                        }
+                    },
+                    "400": {
+                        "description": "value must be \u003e= 1",
+                        "schema": {
+                            "type": "object",
+                            "additionalProperties": true
+                        }
+                    },
+                    "404": {
+                        "description": "node not found",
+                        "schema": {
+                            "type": "object",
+                            "additionalProperties": true
+                        }
+                    }
+                }
+            },
+            "delete": {
+                "tags": [
+                    "Nodes"
+                ],
+                "summary": "Reset a node's max replicas per model to the worker default",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Node ID",
+                        "name": "id",
+                        "in": "path",
+                        "required": true
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "OK",
+                        "schema": {
+                            "type": "object",
+                            "additionalProperties": {
+                                "type": "boolean"
+                            }
+                        }
+                    },
+                    "404": {
+                        "description": "node not found",
+                        "schema": {
+                            "type": "object",
+                            "additionalProperties": true
+                        }
+                    }
+                }
+            }
+        },
         "/api/p2p": {
             "get": {
                 "tags": [
@@ -2951,6 +3035,15 @@ const docTemplate = `{
                 }
             }
         },
+        "localai.UpdateMaxReplicasPerModelRequest": {
+            "type": "object",
+            "properties": {
+                "value": {
+                    "description": "Value is the new per-model replica cap on this node. Must be \u003e= 1.",
+                    "type": "integer"
+                }
+            }
+        },
         "localai.vramEstimateRequest": {
             "type": "object",
             "properties": {
diff --git a/swagger/swagger.json b/swagger/swagger.json
index 907b9594c..fd2f2fd1a 100644
--- a/swagger/swagger.json
+++ b/swagger/swagger.json
@@ -904,6 +904,90 @@
                 }
             }
         },
+        "/api/nodes/{id}/max-replicas-per-model": {
+            "put": {
+                "tags": [
+                    "Nodes"
+                ],
+                "summary": "Update a node's max replicas per model",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Node ID",
+                        "name": "id",
+                        "in": "path",
+                        "required": true
+                    },
+                    {
+                        "description": "New value",
+                        "name": "request",
+                        "in": "body",
+                        "required": true,
+                        "schema": {
+                            "$ref": "#/definitions/localai.UpdateMaxReplicasPerModelRequest"
+                        }
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "OK",
+                        "schema": {
+                            "type": "object",
+                            "additionalProperties": {
+                                "type": "integer"
+                            }
+                        }
+                    },
+                    "400": {
+                        "description": "value must be \u003e= 1",
+                        "schema": {
+                            "type": "object",
+                            "additionalProperties": true
+                        }
+                    },
+                    "404": {
+                        "description": "node not found",
+                        "schema": {
+                            "type": "object",
+                            "additionalProperties": true
+                        }
+                    }
+                }
+            },
+            "delete": {
+                "tags": [
+                    "Nodes"
+                ],
+                "summary": "Reset a node's max replicas per model to the worker default",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Node ID",
+                        "name": "id",
+                        "in": "path",
+                        "required": true
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "OK",
+                        "schema": {
+                            "type": "object",
+                            "additionalProperties": {
+                                "type": "boolean"
+                            }
+                        }
+                    },
+                    "404": {
+                        "description": "node not found",
+                        "schema": {
+                            "type": "object",
+                            "additionalProperties": true
+                        }
+                    }
+                }
+            }
+        },
         "/api/p2p": {
             "get": {
                 "tags": [
@@ -2948,6 +3032,15 @@
                 }
             }
         },
+        "localai.UpdateMaxReplicasPerModelRequest": {
+            "type": "object",
+            "properties": {
+                "value": {
+                    "description": "Value is the new per-model replica cap on this node. Must be \u003e= 1.",
+                    "type": "integer"
+                }
+            }
+        },
         "localai.vramEstimateRequest": {
             "type": "object",
             "properties": {
diff --git a/swagger/swagger.yaml b/swagger/swagger.yaml
index 2a7f8e4cb..93a6f582e 100644
--- a/swagger/swagger.yaml
+++ b/swagger/swagger.yaml
@@ -306,6 +306,13 @@ definitions:
       success:
         type: boolean
     type: object
+  localai.UpdateMaxReplicasPerModelRequest:
+    properties:
+      value:
+        description: Value is the new per-model replica cap on this node. Must be
+          >= 1.
+        type: integer
+    type: object
   localai.vramEstimateRequest:
     properties:
       context_size:
@@ -2714,6 +2721,62 @@ paths:
       summary: Estimate VRAM usage for a model
       tags:
       - config
+  /api/nodes/{id}/max-replicas-per-model:
+    delete:
+      parameters:
+      - description: Node ID
+        in: path
+        name: id
+        required: true
+        type: string
+      responses:
+        "200":
+          description: OK
+          schema:
+            additionalProperties:
+              type: boolean
+            type: object
+        "404":
+          description: node not found
+          schema:
+            additionalProperties: true
+            type: object
+      summary: Reset a node's max replicas per model to the worker default
+      tags:
+      - Nodes
+    put:
+      parameters:
+      - description: Node ID
+        in: path
+        name: id
+        required: true
+        type: string
+      - description: New value
+        in: body
+        name: request
+        required: true
+        schema:
+          $ref: '#/definitions/localai.UpdateMaxReplicasPerModelRequest'
+      responses:
+        "200":
+          description: OK
+          schema:
+            additionalProperties:
+              type: integer
+            type: object
+        "400":
+          description: value must be >= 1
+          schema:
+            additionalProperties: true
+            type: object
+        "404":
+          description: node not found
+          schema:
+            additionalProperties: true
+            type: object
+      summary: Update a node's max replicas per model
+      tags:
+      - Nodes
   /api/p2p:
     get:
       responses: