# Hal0 documentation **URL:** \ **Category:** Start here\ **Created:** [August 22, 2026, 6:49am UTC](https://forum.hal0.dev/t/hal0-documentation/19 "2026-08-22T06:49:15Z")\ **Posts on this page:** 1\ **Page:** 1
**Author:** ![system](https://forum.hal0.dev/user_avatar/forum.hal0.dev/system/32/37_2.png) [@system](https://forum.hal0.dev/u/system)\ **Post date:** [August 22, 2026, 6:49am UTC](https://forum.hal0.dev/t/hal0-documentation/19/1 "2026-08-22T06:49:15Z")
**hal0** turns a Linux box into a polished, OpenAI-compatible inference appliance. It is built for the AMD Ryzen AI Max+ 395 (“Strix Halo”) — iGPU + XDNA NPU + 128 GB of unified memory — and falls back to portable hardware parsers on every other host. Every inference workload runs as its own **podman container** , supervised by a `hal0-slot@.service` systemd unit. A single control plane, `hal0-api` on port `8080`, owns the slot state machines, dispatches OpenAI-compatible `/v1/*` requests to the right slot, and serves the dashboard. There is no shared inference daemon to babysit. Each capability — `utility`, `embed`, `rerank`, `stt`, `tts`, `img`, `vision`, `agent`, and the NPU-conditional `flm-stt` / `flm-embed` slots — runs in its own dedicated podman container. `agent` is the capable default/fallback anchor and `utility` is the cheap helper used for background jobs like memory extraction. ## Hardware support hal0 is first-class on AMD Strix Halo — the Ryzen AI Max+ 395 (128 GB) and the 385 / 390 (64 GB) — with AMD RX 7000-series GPUs also supported. NVIDIA RTX 30/40/50 (via CDI + the NVIDIA Container Toolkit) is experimental, and CPU-only x86\_64 hosts work as a fallback. There is no minimum-spec gate — backend selection degrades to CPU rather than refusing to run. ## What you get - **OpenAI-compatible `/v1/*` API** — chat, completions, embeddings, rerank (`/v1/rerankings`, plus the `/v1/rerank` alias for llama.cpp/Cohere-style clients), audio transcription, speech, and image generation. Point any OpenAI SDK at `http://localhost:8080/v1` and go. - **Hardware-aware slots** — each capability gets its own container, image, flags, port, and lifecycle, sharing only the GPU through an arbiter. - **Profiles** — the whole tune for a slot: llama-server flags, context window, thinking default, vision and MTP (seeds include `chat`, `agent`, `utility`, `coding`, `embedding` and `reranking`). A slot names a profile; to run one model two ways, make two profiles. - **Stacks** — named, exportable bundles of slot + profile + model assignments (built-in `saber`, `forge`, and `pi`) that you can load, clone, and re-apply as a single declarative unit. - **Hardware-anchored install** — `install.sh` probes your hardware and provisions a coherent set of slots, models, and extensions in one pass — no separate setup wizard to run afterward. - **Prewired chat UI** — OpenWebUI on port `3001`, zero config. - **Signed self-update** — cosign-verified tarballs with one-flag rollback. ![hal0 dashboard overview](https://forum.hal0.dev/uploads/default/original/1X/32a23cdb0f40c1b0a9bca19da0380311f5862efe.png) _The hal0 dashboard — slot status, hardware metrics, and quick actions._ ## Start here - [Install hal0](https://forum.hal0.dev/t/install-hal0-hal0-docs/20): One-line install: fetch, verify, unpack, and bring up the API. - [Load your first model](https://forum.hal0.dev/t/load-your-first-model/18): Pull a model from Hugging Face and assign it to a slot. - [Send your first chat](https://forum.hal0.dev/t/send-your-first-chat/17): Chat from OpenWebUI or curl the OpenAI-compatible endpoint. - [Verify the install](https://forum.hal0.dev/t/verify-the-install/109): The six-step ‘did it work’ checklist: health, models, first chat, dashboard, logs, doctor. - [Install on bare metal](https://forum.hal0.dev/t/install-on-bare-metal/15): Run the installer directly on a Linux host, no container layer. - [Install on Proxmox](https://forum.hal0.dev/t/install-on-proxmox/21): Quick-path CT script or the full GPU/NPU passthrough recipe. - [Install in an Incus container](https://forum.hal0.dev/t/install-in-an-incus-container/132): Unprivileged system container on a bare-metal host: GPU/NPU passthrough, clean host, delete to uninstall. - [Install in a rootless podman box (opt-in)](https://forum.hal0.dev/t/install-in-a-rootless-podman-box/140): v1.8.0 opt-in: the whole install in one rootless podman container, GPU/NPU passthrough, a host shim, and an uninstall that removes it all. - [WSL (experimental)](https://forum.hal0.dev/t/quick-start-wsl2-experimental/22): Run hal0 under Windows Subsystem for Linux, CPU-only. - [GPU drivers and memory](https://forum.hal0.dev/t/gpu-drivers-and-memory/16): Kernel/firmware requirements, GTT sizing, and render-group gids. > **Caution: Open on the LAN by default, no TLS** > > `hal0-api` binds `0.0.0.0:8080` and, until you configure an admin key, > treats every request as authenticated by network reachability — the right > posture for a trusted LAN appliance. hal0’s own auth is opt-in (see > [Authentication](https://forum.hal0.dev/t/authentication-hal0-docs/43)). If hal0 is reachable from anywhere you > do not control, front it with a reverse proxy that owns TLS. ## Sections