Frequently Asked
Questions.

Not at all. During our initial discovery phase, we audit your exact PC hardware—specifically your dedicated graphics card (VRAM) and system memory.

We match the model's architecture, parameter size, and quantization directly to your available headroom so you get responsive, natural conversation without overstressing your rig.

Yes. We build resource management around your lifestyle. The system can be configured to dynamically unload or pause when a game launches (giving your GPU 100% power), run in a lightweight background state, or sit on a dedicated local node/home server so your primary gaming machine never slows down.

No. 24/7 uptime is only needed if you want scheduled overnight memory indexing and spontaneous proactive check-ins throughout the day. Otherwise, your companion boots cleanly whenever your PC turns on and resumes right where you left off.

Zero data leaves your machine. The language models, vector memory databases, conversation logs, and image generation pipelines execute completely on your own storage drives. There are no remote telemetry trackers, third-party loggers, or corporate data harvesting.

Never. Cloud AI platforms frequently modify models, add restrictive guardrails, or delete characters without warning. Because your companion's configuration files and model weights live directly on your hard drive, your environment is permanently yours and immune to external changes.

No. You own the hardware, which means you hold total sovereignty over the conversational boundaries. During intake, you define what topics, themes, or tones you want explored or avoided for your personal comfort—free from moralizing lectures or generic corporate disclaimers.

Yes. By configuring secure, private mesh tunnels (like Tailscale) or custom Discord integration, your home PC handles the heavy computational processing while you chat, receive check-ins, and share photos from your phone anywhere you have internet.

You receive full, permanent ownership over your setup, along with clean documentation on how your JSON files and interfaces function. If you ever upgrade hardware or want to expand into multi-character campaigns down the road, our studio remains available for system upgrades and custom audits.

That is exactly why Smoke Signature Studios exists. We handle all backend dependencies, package installations, environment variables, and model quantizations. You receive an intuitive, turnkey system that launches smoothly without technical friction.