GPU Compatibility

NVIDIA GPUs

NVIDIA GPUs with CUDA are the best supported option for ComfyUI.

Supported Cards

VRAM Recommendations

Driver & CUDA & PyTorch Version Matching

Getting the right combination of driver, CUDA, and PyTorch is critical. Here's the compatibility matrix:

Always keep your NVIDIA driver up to date: nvidia.com/Download

AMD GPUs

Windows (DirectML)

AMD GPU support on Windows uses DirectML. Use the Portable Package with the --directml flag. It works but has limitations:

• Performance: Slower than NVIDIA CUDA for the same tier GPU
• Compatibility: Some custom nodes only support CUDA
• Setup: Use the portable package and add --directml flag

Supported cards: RX 6000 series and newer (RDNA2+)

Linux (ROCm)

AMD on Linux uses ROCm, which offers better performance than DirectML. See Manual Install for ROCm PyTorch setup:

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.2.4

Supported cards: RX 6000, RX 7000 series (RDNA2/RDNA3)

Intel GPUs

Intel Arc (XPU)

Intel Arc GPUs have experimental support via the XPU backend:

• Supported: Arc A770, A750, A580
• Status: Experimental — expect some nodes to not work
• Setup: Requires Intel oneAPI toolkit and PyTorch with XPU support

Intel Integrated Graphics

Not recommended. Shared memory is too slow and limited for practical use.

Apple Silicon (macOS)

M1, M2, M3, and M4 chips are supported via the MPS (Metal Performance Shaders) backend:

• Works with unified memory (shared between CPU and GPU)
• M1/M2 with 16 GB: can run SD 1.5 and SDXL
• M3/M4 with 32 GB+: can run Flux and some video models
• Performance is lower than a dedicated NVIDIA GPU

CPU Only

ComfyUI can run on CPU with the --cpu flag. This is very slow and only useful for testing:

• SD 1.5 at 512×512: ~5-10 minutes per image
• SDXL: ~15-30 minutes per image
• Video generation: not practical

RTX 50 Series Setup Guide

The RTX 50 series (5070 Ti, 5080, 5090) is too new for many existing guides. Here's what you need:

1. Update NVIDIA drivers to the latest version (575+)
2. Install PyTorch with CUDA 13.0:

pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu130

3. Known issues:
   • SageAttention may fail to compile — use --use-pytorch-cross-attention as a workaround
   • Some older custom nodes need updates for CUDA 12.8+ compatibility
   • Nunchaku plugin requires specific configuration

If you're stuck with a new 50-series GPU, try Wonderful Launcher first — it's free and can recover the environment without reinstalling. See also Common Issues — RTX 50 Series for more troubleshooting tips.

If ComfyUI starts but fails with Torch not compiled with CUDA enabled, follow the Torch CUDA repair guide to verify the active Python runtime before reinstalling GPU packages.

Related Guides

• ComfyUI Multi GPU - Choose a GPU, run separate instances, and avoid multi-GPU launch mistakes

• System Requirements — Full hardware and software requirements

• Desktop App — Easiest install (NVIDIA only)

• Portable Package — Supports NVIDIA, AMD, and CPU

• Manual Install — Full control, all GPU types

• Common Issues — Solutions for GPU-specific problems

• ComfyUI Out of Memory — Diagnose CUDA OOM, Python RAM, and MPS memory failures

• Dependency Conflicts — When PyTorch CUDA versions clash

• Torch Not Compiled With CUDA Enabled — Repair CPU-only or mismatched PyTorch builds

Source References

• ComfyUI system requirements
• ComfyUI manual installation guide
• PyTorch Start Locally installer