Check out the krun runtime for podman, if you want stronger container isolation from the host. It creates a small VM for each container. Gpu passthrough on linux is limited though.
On my last phone, I succesfully installed sopuli.xyz as a PWA on Android. On my new Android phone, the install “fails” on both firefox and vanadium (chromium), resulting in just a shortcut for a regular web page. Other sites’ PWAs work just fine.
Might something have broken with the PWA part of sopuli?
What models are currently good for running coding tasks? I just ran Qwen3-14B-Q6_K.gguf with llama.cpp on my card with 16GB of vram (+32GB ddr4), but I get really close to filling the entire vram on a single short conversation, so I am looking for some (smaller) alternatives to test.
I might throw OpenCode container in the mix next, if that is relevant information.
podman run --rm --replace --pull=newer \
--name llama \
-p 8080:8080 \
-v ./llama_models:/models:Z \
--device /dev/dri/card1:/dev/dri/card1 \
--device /dev/dri/renderD128:/dev/dri/renderD128 \
ghcr.io/ggml-org/llama.cpp:full-vulkan \
--server \
-m /models/Qwen3-14B-Q6_K.gguf \
-ngl 99 \
-fa on \
-c 16384 \
--temp 0.6 \
--top-k 20 \
--top-p 0.95 \
--jinja \
--host 0.0.0.0 --port 8080
Worked like a charm. Remember to take backups beforehand in any case!