diff --git a/localai/docker-compose.yml b/localai/docker-compose.yml
index 4cb71fd4..2b38d8a5 100644
--- a/localai/docker-compose.yml
+++ b/localai/docker-compose.yml
@@ -7,7 +7,7 @@ services:
       APP_PORT: 8080
       PROXY_AUTH_WHITELIST: "/v1/*"
   api:
-    image: localai/localai:v4.1.0@sha256:736fa3f92dc292108b27a4f68d7441ff7b0baf95e7ee11990411d372d454f895
+    image: localai/localai:v4.1.3@sha256:a6af99e17a73a92caa134e70ae84492cc47b67645c1676268a7522ad14f4c09d
     healthcheck:
       test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]
       interval: 1m
diff --git a/localai/umbrel-app.yml b/localai/umbrel-app.yml
index 5562d277..c74ba921 100644
--- a/localai/umbrel-app.yml
+++ b/localai/umbrel-app.yml
@@ -2,7 +2,7 @@ manifestVersion: 1
 id: localai
 category: ai
 name: LocalAI
-version: "v4.1.0"
+version: "v4.1.3"
 tagline: Drop-in OpenAI replacement
 description: >-
   LocalAI is the free, Open Source OpenAI alternative. LocalAI act as a drop-in replacement REST API that's compatible with OpenAI API specifications for local inferencing.
@@ -15,19 +15,14 @@ description: >-
 
   Before running a model, make sure your device has enough free RAM to support it. Attempting to run a model that exceeds your available memory could cause your device to crash or become unresponsive. Always check the model requirements before downloading or starting it.
 releaseNotes: >-
-  This release turns LocalAI into a production-grade AI platform with distributed clustering, built-in user management, fine-tuning, and much more.
+  This is a patch release with bug fixes and minor improvements.
 
 
   Key highlights include:
-    - Distributed Mode - Run LocalAI as a cluster with smart routing, node groups, drain/resume, and min/max autoscaling
-    - Users & Authentication - Built-in user management with OIDC/OAuth support, invite mode, per-user API keys, and admin impersonation
-    - Quota System - Per-user usage quotas with predictive analytics and usage breakdown dashboards
-    - Fine-Tuning (experimental) - Fine-tune models with TRL, auto-export to GGUF, and import back — all from the UI
-    - Quantization (experimental) - New backend for on-the-fly model quantization
-    - Pipeline Editor - Visual model pipeline editor in the React UI
-    - Standalone Agents - Run agents from the CLI with `local-ai agent run`
-    - Media History - Browse past generated images and media in Studio pages
-    - Various bug fixes including embeddings base64 encoding, Kokoro TTS phonemization, and gallery tag filtering
+    - Fixed login via legacy API keys
+    - Fixed Anthropic API compatibility — no longer emits empty tokens, SSE tool calls corrected
+    - Improved GPU detection for MacOS and Thor
+    - Updated llama.cpp, stable-diffusion.cpp, and ace-step.cpp dependencies
 
 
   Full release notes can be found at https://github.com/mudler/LocalAI/releases