diff --git a/README.md b/README.md
index 48e7ae9..4364c77 100644
--- a/README.md
+++ b/README.md
@@ -93,7 +93,18 @@ To use Llama.cpp with hardware acceleration inside a toolbox container, you must
 > * Extra groups (`video`, `render`, `sudo`) may be required for full access to GPU nodes and compute features, especially with ROCm.
 > * Use `--security-opt seccomp=unconfined` to avoid seccomp sandbox issues (needed for some GPU syscalls).
 
-### 2.1.1 Toolbox Refresh Script (Automatic Updates)
+### 2.1.1 Ubuntu users
+
+Shantur from the Strix Halo Discord server noted that to get these toolboxes to work on Ubuntu, you need to create a Udev rule to allow all users to use GPU or use toolbox with sudo:
+
+Create a udev rule in /etc/udev/rules.d/99-amd-kfd.rules
+
+```
+SUBSYSTEM=="kfd", GROUP="render", MODE="0666", OPTIONS+="last_rule"
+SUBSYSTEM=="drm", KERNEL=="card[0-9]*", GROUP="render", MODE="0666", OPTIONS+="last_rule"
+```
+
+### 2.1.2 Toolbox Refresh Script (Automatic Updates)
 
 To pull the latest container images and recreate toolboxes cleanly, use the provided script: