stevewithington · May 12, 2025 16:25 · May 9, 2025 · May 9, 2025 · May 9, 2025 · May 9, 2025
diff --git a/README.md b/README.md
@@ -9,3 +9,8 @@
 3. Run the compose.yaml here to startup the Open WebUI on port 3000
     - you can run my published compose file directly (without needing to save the YAML locally) with `docker compose -f oci://bretfisher/openwebui up`
 5. Create an admin user and login at http://localhost:3000
+
+More info:
+My YouTube Short on getting started: https://youtube.com/shorts/DRbLUL50-wU
+My YouTube full details video: https://www.youtube.com/watch?v=3p2uWjFyI1U
+Docker Docs: https://docs.docker.com/compose/how-tos/model-runner/
diff --git a/Docker Model Runner Reference.excalidraw.png b/Docker Model Runner Reference.excalidraw.png
diff --git a/Docker Model Runner Reference.excalidraw.png b/Docker Model Runner Reference.excalidraw.png
diff --git a/README.md b/README.md
@@ -2,11 +2,10 @@
 
 1. Enable Docker Model Runner (v4.40 or newer) in Settings or run the command:
     - `docker desktop enable model-runner --no-tcp`
-2. Download some models from https://hub.docker.com/u/ai
+2. Download some models from https://hub.docker.com/u/ai (or let the compose file below pull one for you)
     - `docker model pull ai/qwen2.5:0.5B-F16`
     - `docker model pull ai/smollm2:latest`
     - Be sure to only download models that you have the VRAM to run :)
 3. Run the compose.yaml here to startup the Open WebUI on port 3000
     - you can run my published compose file directly (without needing to save the YAML locally) with `docker compose -f oci://bretfisher/openwebui up`
 5. Create an admin user and login at http://localhost:3000
-
diff --git a/README.md b/README.md
@@ -8,4 +8,5 @@
     - Be sure to only download models that you have the VRAM to run :)
 3. Run the compose.yaml here to startup the Open WebUI on port 3000
     - you can run my published compose file directly (without needing to save the YAML locally) with `docker compose -f oci://bretfisher/openwebui up`
-5. Create an admin user and login at http://localhost:3000
+5. Create an admin user and login at http://localhost:3000
+
diff --git a/compose.yaml b/compose.yaml
@@ -1,3 +1,9 @@
+# This is a Docker Compose file for running the Open WebUI with a specific model.
+# It uses the new provider feature of Compose to specify the model to be downloaded.
+# Note that Open WebUI lets you select any downloaded model, but it won't auto-download them
+# so the provider service will ensure it's downloaded first.
+# https://docs.docker.com/compose/how-tos/model-runner/
+
 services:
   open-webui:
     image: ghcr.io/open-webui/open-webui:main
@@ -8,8 +14,16 @@ services:
       - OPENAI_API_KEY=na
     volumes:
       - open-webui:/app/backend/data
-    restart: always
+    depends_on:
+      - ai-runner
+
+  ai-runner:
+    provider:
+      type: model
+      options:
+        model: ai/gemma3-qat:1B-Q4_K_M # Quantized. Neesds needs 1GB of GPU memory
+        # model: ai/gemma3:4B-F16 # needs at leats 8GB of GPU memory 
+        # https://hub.docker.com/r/ai/gemma3
 
 volumes:
   open-webui:
-
diff --git a/README.md b/README.md
@@ -7,4 +7,5 @@
     - `docker model pull ai/smollm2:latest`
     - Be sure to only download models that you have the VRAM to run :)
 3. Run the compose.yaml here to startup the Open WebUI on port 3000
-4. http://localhost:3000
+    - you can run my published compose file directly (without needing to save the YAML locally) with `docker compose -f oci://bretfisher/openwebui up`
+5. Create an admin user and login at http://localhost:3000
diff --git a/README.md b/README.md
@@ -1,4 +1,4 @@
-# How to use this compose file
+# How to use this compose file to run Open WebUI on a local LLM running with Docker Model Runner
 
 1. Enable Docker Model Runner (v4.40 or newer) in Settings or run the command:
     - `docker desktop enable model-runner --no-tcp`

diff --git a/README.md b/README.md
@@ -0,0 +1,10 @@
+# How to use this compose file
+
+1. Enable Docker Model Runner (v4.40 or newer) in Settings or run the command:
+    - `docker desktop enable model-runner --no-tcp`
+2. Download some models from https://hub.docker.com/u/ai
+    - `docker model pull ai/qwen2.5:0.5B-F16`
+    - `docker model pull ai/smollm2:latest`
+    - Be sure to only download models that you have the VRAM to run :)
+3. Run the compose.yaml here to startup the Open WebUI on port 3000
+4. http://localhost:3000
diff --git a/compose.yaml b/compose.yaml
@@ -0,0 +1,15 @@
+services:
+  open-webui:
+    image: ghcr.io/open-webui/open-webui:main
+    ports:
+      - "3000:8080"
+    environment:
+      - OPENAI_API_BASE_URL=http://model-runner.docker.internal:80/engines/llama.cpp/v1
+      - OPENAI_API_KEY=na
+    volumes:
+      - open-webui:/app/backend/data
+    restart: always
+
+volumes:
+  open-webui:
+
No results found