# Framework Desktop

- [Framework Desktop](#framework-desktop)
  - [BIOS](#bios)
  - [References](#references)
  - [Notes](#notes)
    - [Volume Locations](#volume-locations)
  - [Setup](#setup)
    - [Create the AI user](#create-the-ai-user)
    - [Create the models dir](#create-the-models-dir)
    - [Install the Hugging Face CLI](#install-the-hugging-face-cli)
    - [Download models](#download-models)
      - [Text models](#text-models)
      - [Image models](#image-models)
    - [Create the systemd-ai pod](#create-the-systemd-ai-pod)
  - [llama.cpp](#llamacpp)
  - [stable-diffusion.cpp](#stable-diffusioncpp)
  - [open-webui](#open-webui)
  - [Install the whole thing with quadlets (TM)](#install-the-whole-thing-with-quadlets-tm)

## BIOS

<https://knowledgebase.frame.work/en_us/changing-memory-allocation-amd-ryzen-ai-max-300-series-By1LG5Yrll>

1. Set GPU memory to 96GB
2. Add the following kernel args to /etc/default/grub (set allocatable VRAM to
   112GB): `ttm.pages_limit=28027343750 ttm.page_pool_size=28027343750`
3. Update grub `grub2-mkconfig -o /boot/grub2/grub.cfg`
4. Reboot

## References

<https://docs.podman.io/en/latest/markdown/podman-systemd.unit.5.html>

## Notes

### Volume Locations

`~/.local/share/containers/storage/volumes/`

## Setup

### Create the AI user

```bash
# Create your local ai user. This will be the user you launch podman processes from.
useradd -m ai
loginctl enable-linger ai
su -l ai
mkdir -p ~/.config/containers/systemd/
```

Models are big. You'll want some tools to help find large files quickly when space runs out.

Add this to your .bashrc:

```bash
# Calculate all folder sizes in current dir 
alias {dudir,dud}='du -h --max-depth 1 | sort -h'

# Calculate all file sizes in current dir
alias {dufile,duf}='ls -lhSr'
```

### Create the models dir

```bash
mkdir -p /home/ai/models/{text,image,video}
```

### Install the Hugging Face CLI

<https://huggingface.co/docs/huggingface_hub/en/guides/cli#getting-started>

```bash
# Install
curl -LsSf https://hf.co/cli/install.sh | bash

# Login
hf auth login
```

### Download models

#### Text models

<https://huggingface.co/ggml-org/collections>

```bash
# gpt-oss-120b
mkdir /home/ai/models/text/gpt-oss-120b
hf download --local-dir /home/ai/models/text/gpt-oss-120b ggml-org/gpt-oss-120b-GGUF

# devstral-2-123b
mkdir /home/ai/models/text/devstral-2-123b
hf download --local-dir /home/ai/models/text/devstral-2-123b unsloth/Devstral-2-123B-Instruct-2512-GGUF Q4_K_M/Devstral-2-123B-Instruct-2512-Q4_K_M-00001-of-00002.gguf
hf download --local-dir /home/ai/models/text/devstral-2-123b unsloth/Devstral-2-123B-Instruct-2512-GGUF Q4_K_M/Devstral-2-123B-Instruct-2512-Q4_K_M-00002-of-00002.gguf

# devstral-small-2-24b
mkdir /home/ai/models/text/devstral-small-2-24b
hf download --local-dir /home/ai/models/text/devstral-small-2-24b unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF Devstral-Small-2-24B-Instruct-2512-Q4_K_M.gguf
```

#### Image models

### Create the systemd-ai pod

You'll at least want the ai pod and network. Copy `ai.pod` and `ai.network` out
of `quadlets` into `~/.config/containers/systemd`.

Then run `systemctl --user daemon-reload && systemctl --user start ai-pod`

## llama.cpp

<https://github.com/ggml-org/llama.cpp/tree/master/tools/server>

```bash
# Build the llama.cpp container image
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
export BUILD_TAG=$(date +"%Y-%m-%d-%H-%M-%S")
podman build -t llama-cpp-vulkan:${BUILD_TAG} -t llama-cpp-vulkan:latest -f .devops/vulkan.Dockerfile .

# Run llama server (Available on port 8000)
# Add `--n-cpu-moe 32` to gpt-oss-120b to keep minimal number of expert in GPU
podman run \
--rm \
--name llama-server-demo \
--pod systemd-ai \
--device=/dev/kfd \
--device=/dev/dri \
-v /home/ai/models/text:/models:z \
localhost/llama-cpp-vulkan:2026-01-19-18-00-02 \
--port 8000 \
-c 0 \
-b 2048 \
-ub 2048 \
--perf \
--n-gpu-layers all \
--jinja \
--models-max 1 \
--models-dir /models
```

## stable-diffusion.cpp

```bash
git clone https://github.com/leejet/stable-diffusion.cpp.git
cd stable-diffusion.cpp
git submodule update --init --recursive
export BUILD_TAG=$(date +"%Y-%m-%d-%H-%M-%S")
podman build -f Dockerfile.vulkan -t stable-diffusion-cpp:${BUILD_TAG} -t stable-diffusion-cpp:latest .
```

```bash
# z-turbo
podman run --rm \
-v /home/ai/models:/models:z \
-v /home/ai/output:/output:z \
--device /dev/kfd \
--device /dev/dri \
localhost/stable-diffusion-cpp:latest \
--diffusion-model /models/image/z-turbo/z_image_turbo-Q4_K.gguf \
--vae /models/image/z-turbo/ae.safetensors  \
--llm /models/image/z-turbo/Qwen3-4B-Instruct-2507-Q4_K_M.gguf \
--cfg-scale 1.0 \
-v \
-H 512 \
-W 1024 \
--seed -1 \
--steps 8 \
-o /output/output.png \
-p "A watercolor dragon with flowing ink lines, pastel palette, white paper background, soft brush strokes, high-resolution"

# Edit with flux kontext
podman run --rm \
-v /home/ai/models:/models:z \
-v /home/ai/output:/output:z \
--device /dev/kfd \
--device /dev/dri \
localhost/stable-diffusion-cpp:latest \
--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 \
--seed -1 \
--steps 20 \
-H 512 \
-W 1024 \
-r /output/everquest_logo.png \
-p "change 'EverQuest' to 'EverSteak'" \
-o /output/output.png
```

## open-webui

```bash
# Will be available on port 8080
podman run \
-d \
--pod ai \
-v open-webui:/app/backend/data \
--name open-webui \
--restart always \
ghcr.io/open-webui/open-webui:main
```

## Install the whole thing with quadlets (TM)

```bash
scp -r active/device_framework_desktop/quadlets/* deskwork-ai:.config/containers/systemd/
ssh deskwork-ai
systemctl --user daemon-reload
systemctl --user restart ai-pod.service
```