Tier 1
Train + Serve
7900 XTX · MI210
Flash a USB, boot the AMD box, open the local web app. Models run offline.
Compatibility depends on the card, driver, model, and available memory. Check before release use.
01how
cameo.local:9090That’s the product. After login the box prints that URL. The screenshot above is the real console, not a mock.
02tiers
Tier 1
7900 XTX · MI210
Tier 2
RX 6800 · 6700 XT
Tier 3
RX 580 · APUs
03get it
The next Cameo prerelease is v0.2.0-beta.4. A matching ISO still needs to be built and qualified; the newest public ISO is v0.1.0-beta.2 Lite. Use the release list so a source version is never mistaken for a verified image.
Last public image: v0.1.0-beta.2. Current build pending.
View Lite releasesNext beta: v0.2.0-beta.2. Needs a model — Ollama, Anthropic, or a running Cameo box. Matching standalone artifacts are being rebuilt; no mislabeled binary is offered here.
Knossos 0.2.0-beta.2 CLI plus constitution and license. Build pending.
View Knossos releasesA download appears only after its version and checksum pass the release gate.
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
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:
This installer erases the disk you pick
The selected drive is wiped — partitions, Windows, everything. There is no undo. Nothing is touched until you pick a disk, review the plan, and type that disk’s name (for example sda) to confirm.
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.
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.
A single box does not need Wi-Fi. Cameo Link joins it to a request-level pool; Mesh does not combine VRAM or shard one inference across machines.
iwctl station list station wlan0 scan station wlan0 get-networks station wlan0 connect 'YourSSID'
Pair Cameo Link to the hub with a single-use code. Request routing and pairing are preview; mutual TLS is not available yet. One machine, one card, one house can stay offline after you flash.
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.