From a2cef18efe0d1ff832916394f8b0ba1adf54a59a Mon Sep 17 00:00:00 2001
From: ducoterra <git@ducoterra.net>
Date: Wed, 7 Jan 2026 09:28:29 -0500
Subject: [PATCH] Add framework desktop LLM instructions

---
 .../framework_desktop.md                      | 103 ++++++++++++++++++
 1 file changed, 103 insertions(+)
 create mode 100644 active/device_framework_desktop/framework_desktop.md

diff --git a/active/device_framework_desktop/framework_desktop.md b/active/device_framework_desktop/framework_desktop.md
new file mode 100644
index 0000000..617f560
--- /dev/null
+++ b/active/device_framework_desktop/framework_desktop.md
@@ -0,0 +1,103 @@
+# Framework Desktop
+
+## 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
+
+## Docker
+
+```bash
+dnf config-manager addrepo \
+--from-repofile https://download.docker.com/linux/fedora/docker-ce.repo
+
+dnf install \
+docker-ce \
+docker-ce-cli \
+containerd.io \
+docker-buildx-plugin \
+docker-compose-plugin
+```
+
+## Llama.cpp
+
+```bash
+# Build the llama.cpp docker image
+git clone https://github.com/ggml-org/llama.cpp.git
+export BUILD_TAG=$(date +"%Y-%m-%d-%H-%M-%S")
+docker build -t llama-cpp-vulkan:${BUILD_TAG} -f .devops/vulkan.Dockerfile .
+
+# Run llama server
+docker run \
+-d \
+--restart always \
+--name=llama-server \
+--network=host \
+--device=/dev/kfd \
+--device=/dev/dri \
+-v llama-server-cache:/root/.cache \
+llama-cpp-vulkan:${BUILD_TAG} \
+-hf ggml-org/gpt-oss-120b-GGUF  --ctx-size 0 --jinja -ub 2048 -b 2048 \
+--port 8000 --host 0.0.0.0 -n -1 --n-gpu-layers 999
+
+# Firewall
+firewall-cmd --add-port=8000/tcp --permanent
+firewall-cmd --reload
+```
+
+## Ollama
+
+```bash
+# Run ollama
+# Will be available on port 11434
+docker run \
+-d \
+--restart always \
+--device /dev/kfd \
+--device /dev/dri \
+-v ollama:/root/.ollama \
+-e OLLAMA_VULKAN=1 \
+--name ollama \
+--network host \
+docker.io/ollama/ollama:0.13.5
+
+# Run an image
+docker exec -it ollama ollama run gpt-oss:20b
+
+# Firewall
+firewall-cmd --add-port=11434/tcp --permanent
+firewall-cmd --reload
+```
+
+## Anything LLM
+
+Per [the docs](https://docs.anythingllm.com/installation-docker/cloud-docker):
+
+> Note --cap-add SYS_ADMIN is a required command if you want to scrape webpages.
+> We use PuppeeteerJS to scrape websites links and --cap-add SYS_ADMIN lets us
+> use sandboxed Chromium across all runtimes for best security practices
+
+```bash
+# Server will be accessible on port 3001
+# Connect llama.cpp as a generic OpenAI LLM provider and use host
+# http://172.17.0.1:8000/v1
+# Chat model name doesn't matter.
+docker run \
+-d \
+--restart always \
+--network host \
+--name anythingllm \
+--cap-add SYS_ADMIN \
+-v anythingllm:/app/server/storage \
+-e STORAGE_DIR="/app/server/storage" \
+docker.io/mintplexlabs/anythingllm
+
+# Firewall
+firewall-cmd --add-port=3001/tcp --permanent
+firewall-cmd --reload
+```
\ No newline at end of file