cameo how tiers deck download github

any AMD card.
serves LLMs.

Flash Cameo to a USB, boot an AMD machine, and open the local web app. Models run offline.

RX 580RX 68007900 XTXMI210APUs
Download Cameo

Free • Open source • Apache 2.0

GitHub

01how it works

Download. Plug it in. Set an account. Play.

Cameo is an appliance, not a toolchain. The USB already carries the OS. Install copies that image onto disk — it downloads nothing. After reboot the box serves on your LAN with the cables pulled.

01

Download

One ISO, while you still have a network. Universal if you're unsure; lite if you know the card is Vulkan-only.

02

Plug in

Flash a USB, boot the AMD machine. Install Cameo to disk is the default menu entry.

03

Account

Pick a disk, set an admin username and password. A console key is written for you.

04

Play

Open :9090 from the LAN. A starter model (qwen2.5-0.5b) is already on disk. Chatting does not need the internet.

  first boot · tty1
================  Cameo  ================  RX 580 8G · Tier 3 · vulkan OK Web console:  http://192.168.1.40:9090  Console key:  K7m…  Log in as the admin you created.  No internet required to serve.

02what your card does

Three tiers. Vulkan on all of them.

Cameo never silently fails on unsupported hardware. It classifies the card and says so in plain language. Training needs ROCm (tiers 1–2). Inference does not.

Tier 1

Train + Serve

7900 XTX · MI210

train
serve

Official ROCm. Vulkan fallback. This is the card you train on.

Tier 2

Serve

RX 6800 · 6700 XT

train
serve

Inference on day one. Training is community-tested via HSA override, not official ROCm.

Tier 3

Vulkan Inference

RX 580 · APUs

train
serve

No usable ROCm path. Vulkan-only inference. Still a working LLM box.

  first boot · tty1
================  Cameo  ================GPU 0  Radeon RX 580 8G  pci  0000:01:00.0  vram 8192 MiB  arch gfx803  tier ● Tier 3   no training  why  gfx803 has no usable ROCm path:        Vulkan-only inference, no training.-----------------------------------------Web console:  http://192.168.1.40:9090

That's the real first-boot printout for a tier-3 drawer card — the tier in plain language, the reason, then the console URL. Check yours with cameo gpu-status; the tier is a smart default, not a verdict.

03the console

Administer it from a browser.

cameod starts on boot and binds :9090 with a key. GPUs, endpoints, a playground — on your LAN. Drop a GGUF, chat. No cloud, no extra web stack.

04the Deck

See the model, its owner, and the proof.

See what is running, how much memory it uses, who owns the session, and whether the work passed verification.

RUNNING

Model status

Backend, context, endpoint, and lease status for every model.

MEMORY

Capacity

See free memory and which session holds each model.

RESULT

Verification

Review changed files, verification results, and the trace.

ACCESS

Permissions

Consumer keys run models. Operator keys manage models and leases.

  Cameo Engine Contract v1
consumer  GET /api/engines  -> models, profiles, limits, capabilitiesconsumer  POST /v1/chat/completions  -> OpenAI JSON + SSE streamingoperator  POST /api/servers  -> deliberately provision a cold modelsession   POST /api/sessions/{id}/lease  -> protect a running modeltools     agent-managed fallback  -> no assumed server-specific dialectCameo observes the work. Daedalus owns the agent loop.

05one card → a cluster

Same two commands on 1, 4, or 9 cards.

Connect additional Cameo boxes over Ethernet or Wi-Fi and manage them as one fleet.

one card ×1 a box ×4 a cluster ×9 one card ×1 a box ×4 a cluster ×9

06get it

Image. Flash. That’s the whole path.

Download the ISO, write it to a USB, and boot the machine. A starter model is included, so local chat works after installation.

flash cameo-*.iso → boot Install Cameo to disk → chat cameo.local:9090

1 · Download the image

Take the file named cameo-*.iso (or .iso.part* if it was split). Ignore “Source code” zip/tar — those are not flashable. If the newest tag has no ISO yet, use the last tag that lists one.

UniversalVulkan + ROCm

Includes both AMD runtime paths. ROCm is enabled only on supported cards; other compatible AMD GPUs use Vulkan.

Download Universal ISO

SHA-256 checksum

Litesmaller · vulkan only

For Vulkan-capable AMD hardware that does not need the much larger ROCm training stack.

Download Lite ISO

SHA-256 checksum

Daedalus standalone harness

Run the Rust-native daedalus harness on an existing Windows workstation with the validated archive below. Verify the archive before opening it.

Windowsx86_64

Standalone daedalus.exe plus documentation.

Download Windows zip

SHA-256 checksum

Linux + macOScoming later

Packages will appear here after their release builds pass validation.

2 · Flash a USB

Windows: Rufus in DD Image mode (ISO mode often will not boot), or Etcher. Linux/macOS: Etcher, or:

sudo dd if=cameo-*.iso of=/dev/sdX bs=4M status=progress oflag=sync

3 · Plug it in, set an account

Disable Secure Boot (or the stick is ignored and Windows boots). Put the USB in the AMD machine. Install Cameo to disk is already the default entry. It shows the detected GPU and tier, then asks for:

which disk to erase admin username admin password

Nothing is downloaded. The installer copies the live image onto that disk, writes a console key, and enables cameod. Then reboot and pull the USB.

4 · Play, offline

From a laptop or phone on the same LAN (plug the box into Ethernet if it has a port), open the URL printed after login — http://cameo.local:9090 or the IP. Enter the key. Start qwen2.5-0.5b (smoke test, already on disk). Chatting never phones home. Extra GGUFs: drop them in /var/lib/cameo/models.

Fleet: that’s when you connect Wi-Fi

A single box does not need Wi-Fi. Join a fleet of nodes — then give that node a network so it can attach:

Ethernet — plug in, DHCP is automatic Wi-Fi — iwctl on that node only extra models — cameo pull 
iwctl
  station list
  station wlan0 scan
  station wlan0 get-networks
  station wlan0 connect 'YourSSID'

Then cameo fleet / hub URL on that node. One machine, one card, one house: stay air-gapped after you flash.

Developers: container or build the ISO yourself

Container — host owns the GPU driver:

podman build -f containers/Containerfile -t cameo:vulkan .
podman run --rm -p 9090:9090 \
  -v cameo-models:/var/lib/cameo/models \
  --device=/dev/kfd --device=/dev/dri \
  --group-add video --group-add render \
  cameo:vulkan

Build the ISO on an Arch host:

git clone https://github.com/sadlowskik/Cameo
sudo ./scripts/build-iso.sh
sudo CAMEO_EDITION=lite ./scripts/build-iso.sh

Beta, pre-v1. Flash an .iso, not Source code. Check SHA256SUMS. The disk installer erases the drive you pick. Source: github.com/sadlowskik/Cameo.