diff --git a/.github/workflows/generate-release.yml b/.github/workflows/generate-release.yml
index ebcd0c988..82d08d0b4 100644
--- a/.github/workflows/generate-release.yml
+++ b/.github/workflows/generate-release.yml
@@ -17,7 +17,7 @@ jobs:
 
     strategy:
       matrix:
-        type: [ llamacpp, ollama ]
+        type: [ llamacpp-cpu, ollama ]
 
     permissions:
       contents: read
diff --git a/Dockerfile.llamacpp b/Dockerfile.llamacpp-cpu
similarity index 100%
rename from Dockerfile.llamacpp
rename to Dockerfile.llamacpp-cpu
diff --git a/docker-compose.yaml b/docker-compose.yaml
index 8c6943813..a5df4647e 100644
--- a/docker-compose.yaml
+++ b/docker-compose.yaml
@@ -7,7 +7,7 @@ services:
   # Private-GPT service for the Ollama CPU and GPU modes
   # This service builds from an external Dockerfile and runs the Ollama mode.
   private-gpt-ollama:
-    image: ${PGPT_IMAGE:-zylonai/private-gpt}${PGPT_TAG:-0.6.1}-external
+    image: ${PGPT_IMAGE:-zylonai/private-gpt}${PGPT_TAG:-0.6.1}-ollama
     build:
       context: .
       dockerfile: Dockerfile.ollama
@@ -30,11 +30,11 @@ services:
 
   # Private-GPT service for the local mode
   # This service builds from a local Dockerfile and runs the application in local mode.
-  private-gpt-local:
-    image: ${PGPT_IMAGE:-zylonai/private-gpt}${PGPT_TAG:-0.6.1}-local
+  private-gpt-llamacpp-cpu:
+    image: ${PGPT_IMAGE:-zylonai/private-gpt}${PGPT_TAG:-0.6.1}-llamacpp-cpu
     build:
       context: .
-      dockerfile: Dockerfile.llamacpp
+      dockerfile: Dockerfile.llamacpp-cpu
     volumes:
       - ./local_data/:/home/worker/app/local_data
       - ./models/:/home/worker/app/models
@@ -46,7 +46,7 @@ services:
       PGPT_PROFILES: local
       HF_TOKEN: ${HF_TOKEN}
     profiles:
-      - llamacpp
+      - llamacpp-cpu
 
   #-----------------------------------
   #---- Ollama services --------------
diff --git a/fern/docs/pages/quickstart/quickstart.mdx b/fern/docs/pages/quickstart/quickstart.mdx
index 70423e453..9bcb8804b 100644
--- a/fern/docs/pages/quickstart/quickstart.mdx
+++ b/fern/docs/pages/quickstart/quickstart.mdx
@@ -78,7 +78,7 @@ A **Hugging Face Token (HF_TOKEN)** is required for accessing Hugging Face model
 **Run:**
 Start the services with your Hugging Face token using pre-built images:
 ```sh
-HF_TOKEN=<your_hf_token> docker-compose up --profile llamacpp
+HF_TOKEN=<your_hf_token> docker-compose up --profile llamacpp-cpu
 ```
 Replace `<your_hf_token>` with your actual Hugging Face token.