From 5b79da95fd7cf79b63fbe2b9de3dd6c220899b08 Mon Sep 17 00:00:00 2001
From: ducoterra <git@ducoterra.net>
Date: Fri, 6 Feb 2026 20:19:10 -0500
Subject: [PATCH] add local ai podman docs

---
 active/podman_localai/localai.md | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/active/podman_localai/localai.md b/active/podman_localai/localai.md
index 6da2156..ca61beb 100644
--- a/active/podman_localai/localai.md
+++ b/active/podman_localai/localai.md
@@ -2,6 +2,7 @@
 
 - [Local AI with Anything LLM](#local-ai-with-anything-llm)
   - [Useful links I keep losing](#useful-links-i-keep-losing)
+  - [Podman](#podman)
   - [Running Local AI on Ubuntu 24.04 with Nvidia GPU](#running-local-ai-on-ubuntu-2404-with-nvidia-gpu)
   - [Running Local AI on Arch with AMD GPU](#running-local-ai-on-arch-with-amd-gpu)
   - [Running Anything LLM](#running-anything-llm)
@@ -32,6 +33,12 @@
 - [Example model config files from gallery](https://github.com/mudler/LocalAI/tree/master/gallery)
 - [List of all available models](https://github.com/mudler/LocalAI/blob/master/gallery/index.yaml)
 
+## Podman
+
+```bash
+docker run -ti --name local-ai -p 8081:8080 --device=/dev/kfd --device=/dev/dri --group-add=video --replace localai/localai:latest-gpu-vulkan
+```
+
 ## Running Local AI on Ubuntu 24.04 with Nvidia GPU
 
 ```bash
@@ -124,7 +131,7 @@ pipx install "huggingface_hub[cli]"
 podman network create --ipv6 --label local-ai local-ai
 
 # You might want to mount an external drive here.
-export MODEL_DIR=/models
+export MODEL_DIR=/srv/models
 mkdir -p $MODEL_DIR
 
 # LOCALAI_SINGLE_ACTIVE_BACKEND will unload the previous model before loading the next one
@@ -136,14 +143,13 @@ mkdir -p $MODEL_DIR
 podman run \
 -d \
 -p 8080:8080 \
--e LOCALAI_API_KEY=$(cat ~/.localai/token) \
 -e LOCALAI_SINGLE_ACTIVE_BACKEND=true \
 --device /dev/dri \
 --device /dev/kfd \
 --name local-ai \
---network local-ai \
--v $MODEL_DIR:/build/models \
--v localai-tmp:/tmp/generated \
+--replace \
+-v $MODEL_DIR:/build/models:z \
+-v localai-tmp:/tmp/generated:z \
 quay.io/go-skynet/local-ai:master-hipblas-ffmpeg
 
 # The second (8081) will be our frontend. We'll protect it with basic auth.
@@ -153,9 +159,9 @@ podman run \
 -d \
 -p 8081:8080 \
 --name local-ai-webui \
---network local-ai \
--v $MODEL_DIR:/build/models \
--v localai-tmp:/tmp/generated \
+--replace \
+-v $MODEL_DIR:/build/models:z \
+-v localai-tmp:/tmp/generated:z \
 quay.io/go-skynet/local-ai:master-hipblas-ffmpeg
 ```