Saient says my GPU isn't being used.

Saient ships a CUDA engine for NVIDIA GPUs and falls back to CPU if no GPU is detected. Make sure your NVIDIA driver is installed and nvidia-smi works. The title bar shows live GPU stats when a model is loaded.

Where do I put model files?

Saient scans its models folder for GGUF files. Drop your .gguf models there (or use the in-app picker) and they appear in the model list.

Help & Setup — Saient

Install

Saient runs on Linux and Windows. Download the build for your OS from the download section.

Linux — grab the .AppImage (make it executable and run it) or install the .deb on Debian/Ubuntu.
Windows — run the .exe installer and follow the prompts.

An NVIDIA GPU is recommended for fast inference — Saient bundles its own CUDA engine, so you don’t need to install CUDA yourself. No GPU? It still runs on CPU.

First run & setup

The first time you open Saient, a setup wizard walks you through getting ready:

Fast setup — just the essentials; the AI engine is bundled, so chat and the agent work right away.
Full setup — also installs the optional Python tools (in a managed virtual environment) for image generation, the vision analyzer, text-to-speech and LoRA training.

You can re-run setup or install extras later from inside the app.

Loading models

Saient uses GGUF models. Place your .gguf files in Saient’s models folder (shown in the app) and they’ll appear in the model list — pick one and click load.

Well-supported families include Qwen, gpt-oss, Llama, Mistral and OLMoE, across common quantisations (Q4_K, Q5_K, Q6_K, Q8_0 and several IQ types).

Bigger models need more VRAM. If a model fails to load, try a smaller quantisation (e.g. a Q4_K build) or a smaller model.

GPU & CUDA

Saient ships with a prebuilt CUDA engine and the one small CUDA runtime library it needs — there’s nothing extra to install. On launch it detects your NVIDIA GPU and uses it automatically; if none is found it falls back to CPU.

Make sure your NVIDIA driver is installed and up to date.
When a model is loaded, the title bar shows live GPU stats so you can confirm it’s on the GPU.

The studios

Switch studios from the icon rail on the left.

Chat — talk to your local model; it renders live HTML artifacts in a side pane.
Agent — a real coding agent with a terminal and a plan→act→verify loop. Toggle it with Ctrl·Shift·K. Write mode is off by default for safety.
Image Gen — SDXL text-to-image with LoRA, schedulers and an optional face-detail pass.
Vision — ask questions about an image; the analyzer describes and answers locally.
Text-to-Speech — natural offline voices.
LoRA & Merge — train SDXL LoRAs and merge checkpoints.

Press ? any time for the full keyboard-shortcut list.

Launch password

You can set a launch password so the app asks for it on start — handy on a shared computer. Open the 🔒 button in the title bar to set, change, or remove it.

The launch password deters casual access to the app. It does not encrypt the files on your disk — treat it as a lock on the front door, not a safe.

Troubleshooting

A model won’t load or the app feels stuck

The model may be too large for your VRAM. Try a smaller quantisation or model. Stopping and reloading the model from the title bar clears the engine.

Image gen / vision / TTS aren’t available

These need the optional Python tools. Re-run Full setup to install them.

The GPU isn’t being used

Confirm your NVIDIA driver works (nvidia-smi on the command line). Without a usable GPU, Saient runs on CPU, which is slower.

FAQ

Does turning off my PC kill Saient?

No — it sleeps. Saient keeps its state on disk: its goals, its drives, what it has done and what it was part-way through. Shutting down stops it running; starting up loads that state and carries on from where it was. Nothing breaks and nothing is lost.

What actually ends a Saient, then?

Deleting its state files. That is the one thing that cannot be undone. Start it again afterwards and you get a new one beginning from nothing, rather than the same one continuing. Everything else — closing the app, a crash, a reboot, days of not opening it — is sleep.

Is Saient conscious?

No, and we are not claiming it is. “Sleep” describes what happens to its saved state, not an experience. What Saient actually has is continuity: it does not start from a blank slate each time, and what it did last session still shapes what it does next. That is a property of the software, and it is worth naming honestly rather than dressing up.

Does Saient keep running when I close the app?

No. Nothing keeps ticking in the background once Saient is closed, and nothing phones home while it sleeps. It only runs while the app is open and you have chosen a level that runs it.

How much does it cost?

Nothing. Saient is free — no subscription, no unlock, no account.

Does Saient send my data anywhere?

No. Inference and the agent both run on your machine. The only time data leaves is when you choose to download a model. See our privacy policy.

Can I use it offline?

Yes — after downloading the app and your models, Saient works fully offline.

Which operating systems are supported?

Linux and Windows. An NVIDIA GPU is recommended but not required.