local ai checkpoint

active/device_framework_desktop/quadlets/llama-server.container

@@ -2,21 +2,29 @@
 Description=A Llama CPP Server Running GPT OSS 120b
 
 [Container]
+# Shared AI pod
 Pod=ai.pod
-Image=localhost/llama-cpp-vulkan:2026-01-12-10-13-30
-Volume=llama-server-cache:/root/.cache
+
+# Image is built locally via podman build
+Image=localhost/llama-cpp-vulkan:latest
+
+# Downloaded models volume
+Volume=/home/ai/models/text:/models:z
+
+# GPU Device
 AddDevice=/dev/kfd
 AddDevice=/dev/dri
 
-Exec=-hf ggml-org/gpt-oss-120b-GGUF \
---ctx-size 32000 \
---jinja \
--ub 2048 \
--b 2048 \
---port 8000 \
---host 0.0.0.0 \
--n -1 \
---n-gpu-layers 999
+# Server command
+Exec=--port 8000 \
+    -c 0 \
+    -b 2048 \
+    -ub 2048 \
+    --perf \
+    --n-gpu-layers all \
+    --jinja \
+    --models-max 1 \
+    --models-dir /models
 
 [Service]
 Restart=always