Will Promptus run on your machine?

Promptus generates locally, so what you can make depends on your GPU. It runs across a wide range of hardware — from a GTX 1060 to an RTX 5090, and on Apple Silicon. Here is exactly what runs at each tier.

What runs at each hardware tier

Every tier generates locally. The tier decides how big a model you can load and how fast it finishes.

Minimum

Entry hardware

NVIDIA GTX 1060 6 GB or better

Or CPU-only, which works but is slow

  • Stable Diffusion 1.5 and SDXL images
  • Z-Image Turbo — about 2s per generation
  • Hunyuan 3D, fast mode
  • Qwen3 7B, Mistral 7B, Phi-4
  • Lightweight CosyFlows
  • Wan 2.1 video — slow, short clips only
★ Recommended

The comfortable tier

NVIDIA RTX 3060 12 GB or better

Or Apple M2 / M3 with 16 GB unified memory

  • Flux.1 Dev at full image quality
  • Stable Diffusion 3.5 Medium
  • Wan 2.1 video at 720p, comfortably
  • Qwen3 14B and Phi-4 14B for text and agents
  • DeepSeek-R1 32B for coding agents
  • The full CosyFlows library
Full power

No compromises

NVIDIA RTX 4070 or above, up to RTX 5090

Or Apple M3 Max with 36 GB or more

  • LTX-2 and LTX-2.3 video — smooth
  • Wan 2.1 video at 1080p — smooth
  • Flux.1 Dev in large batches
  • Llama 3.3 70B at full quality and speed
  • Qwen3 30B and 72B variants
  • Full multi-step OpenClaw agents
Mac

Apple Silicon

Apple M1 or later, 8 GB unified memory

macOS 12 Monterey or later

  • All Apple Silicon chips are supported
  • M1 8 GB: basic image generation
  • M2 / M3 16 GB: the recommended Mac tier
  • M3 Max / M4 Pro: full video speed
  • Intel Macs: CPU-only mode

No compatible GPU? Promptus also supports cloud-backed generation through API routing. It is slower than local, but it works — and it is the right option while you wait on hardware.

AMD cards: Radeon support is on the roadmap, not shipped. If you have an AMD GPU today, use CPU-only mode or the cloud plan.

Common questions

Tap a question to see the answer.

Your machine qualifies. Now own the app.

One payment of $49 and Promptus is yours — unlimited local generation, no subscription, no per-image fees.

Not sure your setup qualifies? Email support@promptus.ai with your specs and we will tell you exactly what will run.