System requirements

The short version

• Windows 10/11 only. There is no macOS, Linux, or Android version today.
• Local generation needs an NVIDIA GPU, GTX 16-series or newer. Turing is the oldest architecture the local engine supports, so a GTX 1660 runs and a GTX 1080 does not. AMD and Intel GPUs are not supported for local generation (the engine is CUDA-based).
• Virtual machines and rented Windows desktops are not a supported setup. That includes Windows in a virtual machine on a Mac, which has no NVIDIA GPU to pass through in the first place. See Virtual machines and rented GPUs.
• Cloud generation works on any PC. It runs on SimpliGen's GPUs, so your graphics card doesn't matter. If your GPU is below the requirements, Cloud is the intended path.

What your GPU can run locally

Not sure which row you are in? Check your GPU answers it from four questions, with no sign-up.

Also plan for:

• RAM: 16 GB minimum, 32 GB recommended for video. Video models spill into system RAM heavily; more RAM genuinely helps.
• Disk: models are large (single video models can be 10-30 GB). Set your storage location in Settings -> Storage before installing big presets. Models stay on disk when you uninstall a preset, because presets share them; see Freeing up disk space when you need it back.
• Windows page file: heavy video generation can need a large page file. If generations crash near the end, see Out of memory.

Many presets ship several variants (for example fp8 and GGUF builds of the same model). The app picks a variant that fits your GPU, and the preset card lets you choose; a smaller variant trades some quality for fitting into less VRAM.

GTX 16-series cards: GTX 1650, 1660, 1660 Super, 1660 Ti

These are the oldest cards the engine runs, and they sit in the 4 to 6 GB row above: images yes, local video no. Three things are worth knowing before you buy.

• Local video has outgrown them. The current video presets do not finish on 6 GB. Cloud generation is the video route on these cards, and it runs on our GPUs, so the card stops mattering.
• 4 GB is the floor, and system RAM decides it. On a 4 GB card, read 16 GB of system RAM as part of the requirement rather than a recommendation: in our own telemetry 4 GB cards with 16 GB of system RAM finish image runs, and the same cards with 8 GB mostly do not.
• Images take longer than the times quoted for RTX cards. A 16-series card is older, not merely smaller, and VRAM decides what fits while the card's generation decides how fast it gets there.

How long does a generation take?

Local generation takes minutes, not seconds. That is normal. Rough expectations:

• Images: seconds to a couple of minutes on most supported cards.
• Video on a 16 GB+ desktop card: a few minutes for a 5-second 480p clip; high resolutions take much longer.
• Video on an 8 GB card (especially laptops): 30-60 minutes for a 5-second clip on a lightweight preset is within normal range.

Start at 480p and 5 seconds to validate a prompt, then scale up. Every resolution tier and extra second multiplies VRAM use and time. Cloud generation is much faster because it runs on datacenter GPUs.

Cards and setups that do NOT work locally

• AMD and Intel GPUs: not supported. On the wishlist, but with no timeline.
• NVIDIA GTX 10-series and older (GTX 1080, 1060, 1050 Ti...): the engine's CUDA build carries no kernels below sm_75, and these cards are below it. You may see CUDA error: no kernel image is available for execution on the device. The GTX 16-series is the first generation above that line, which is why it runs and these do not.
• Workstation cards from the same era (Quadro M6000, P5000...): same architecture limitation.
• Macs: the installer is a Windows .exe; it will not run on macOS.
• Phones / tablets: no.

If the installer or engine reports UNSUPPORTED_HARDWARE, your GPU falls into one of the groups above.

Virtual machines and rented GPUs

Running SimpliGen inside a VM or on a virtualized GPU (Azure, some rented cloud desktops) is hit-or-miss: virtual GPUs often lack memory-management features the engine uses. If the engine crashes on a vGPU, enable Virtual GPU compatibility in Settings. Renting a GPU server (RunPod and similar) to run SimpliGen remotely is not a supported setup; use built-in Cloud generation instead.

Windows in a virtual machine on a Mac is a separate case, and the answer there is a flat no for local generation. Apple hardware has no NVIDIA GPU, so there is nothing for the VM to pass through and no setting that changes it. The routes on a Mac are Cloud generation (which needs a Windows PC to run the app) or ComfyUI itself, which supports Apple silicon.

Multiple GPUs

SimpliGen uses one GPU. If you have several, the app picks the most capable one. Multi-GPU pooling is not supported.