local ai checkpoint

active/device_framework_desktop/quadlets/ai.network

@@ -0,0 +1,2 @@
+[Network]
+IPv6=true

active/device_framework_desktop/quadlets/ai.pod

@@ -1,9 +1,8 @@
 [Pod]
+Network=ai.network
 # llama.cpp
 PublishPort=8000:8000/tcp
 # open-webui
 PublishPort=8080:8080/tcp
-# anything-llm
-PublishPort=3001:3001/tcp
-# ollama
-PublishPort=11434:11434/tcp
+# stable-diffusion.cpp
+PublishPort=1234:1234/tcp

active/device_framework_desktop/quadlets/anything-llm.container

@@ -1,21 +0,0 @@
-[Unit]
-Description=An Anything LLM Frontend for Local AI Services
-
-[Container]
-Pod=ai.pod
-Image=docker.io/mintplexlabs/anythingllm
-Volume=anythingllm:/app/server/storage
-Volume=/home/ai/anything-llm/.env:/app/server/.env:z
-Environment=STORAGE_DIR=/app/server/storage
-AddCapability=SYS_ADMIN
-User=1000
-Group=1000
-
-[Service]
-Restart=always
-# Extend Timeout to allow time to pull the image
-TimeoutStartSec=900
-
-[Install]
-# Start by default on boot
-WantedBy=multi-user.target default.target

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

active/device_framework_desktop/quadlets/ollama-server.container

@@ -1,19 +0,0 @@
-[Unit]
-Description=An Ollama Server
-
-[Container]
-Pod=ai.pod
-Image=docker.io/ollama/ollama:0.13.5
-Volume=ollama:/root/.ollama
-AddDevice=/dev/kfd
-AddDevice=/dev/dri
-Environment=OLLAMA_VULKAN=1
-
-[Service]
-Restart=always
-# Extend Timeout to allow time to pull the image
-TimeoutStartSec=900
-
-[Install]
-# Start by default on boot
-WantedBy=multi-user.target default.target

active/device_framework_desktop/quadlets/open-webui.container

@@ -2,8 +2,13 @@
 Description=An Open Webui Frontend for Local AI Services
 
 [Container]
+# Shared AI pod
 Pod=ai.pod
+
+# Open Webui base image
 Image=ghcr.io/open-webui/open-webui:main
+
+# Nothing too complicated here. Open Webui will basically configure itself.
 Volume=open-webui-data:/app/backend/data
 
 [Service]

active/device_framework_desktop/quadlets/stable-diffusion-edit-server.container

@@ -0,0 +1,41 @@
+[Unit]
+Description=A Stable Diffusion CPP Server for Editing Images
+
+[Container]
+# Shared AI pod
+Pod=ai.pod
+
+# Vulkan image for AMD GPU
+Image=localhost/stable-diffusion-cpp:latest
+
+# Shared models directory
+Volume=/home/ai/models:/models:z
+
+# GPU Device
+AddDevice=/dev/kfd
+AddDevice=/dev/dri
+
+# Override entrypoint to use server
+Entrypoint=/sd-server
+
+# Server args
+Exec=-l 0.0.0.0 \
+    --listen-port 1235 \
+    --diffusion-model /models/image/flux-1-kontext/flux1-kontext-dev-Q4_K_M.gguf \
+    --vae /models/image/flux-1-kontext/ae.safetensors \
+    --clip_l /models/image/flux-1-kontext/clip_l.safetensors \
+    --t5xxl /models/image/flux-1-kontext/t5xxl_fp16.safetensors \
+    --cfg-scale 1.0 \
+    --sampling-method euler \
+    -v \
+    --seed -1 \
+    --steps 28
+
+[Service]
+Restart=always
+# Extend Timeout to allow time to pull the image
+TimeoutStartSec=900
+
+[Install]
+# Start by default on boot
+WantedBy=multi-user.target default.target

active/device_framework_desktop/quadlets/stable-diffusion-gen-server.container

@@ -0,0 +1,41 @@
+[Unit]
+Description=A Stable Diffusion CPP Server for Generating Images
+
+[Container]
+# Shared AI pod
+Pod=ai.pod
+
+# Vulkan image for AMD GPU
+Image=localhost/stable-diffusion-cpp:latest
+
+# Shared models directory
+Volume=/home/ai/models:/models:z
+
+# GPU Device
+AddDevice=/dev/kfd
+AddDevice=/dev/dri
+
+# Override entrypoint to use server
+Entrypoint=/sd-server
+
+# Server args
+Exec=-l 0.0.0.0 \
+    --listen-port 1234 \
+    --diffusion-model /models/image/z-turbo/z_image_turbo-Q4_K.gguf \
+    --vae /models/image/z-turbo/ae.safetensors  \
+    --llm /models/image/z-turbo/qwen_3_4b.safetensors \
+    -l 0.0.0.0 \
+    --listen-port 1234 \
+    --cfg-scale 1.0 \
+    -v \
+    --seed -1 \
+    --steps 8
+
+[Service]
+Restart=always
+# Extend Timeout to allow time to pull the image
+TimeoutStartSec=900
+
+[Install]
+# Start by default on boot
+WantedBy=multi-user.target default.target