# Can I run Qwen-Image on Apple M4 Max (64GB)?

Updated: 2026-06-15

**Yes, it runs.** Runs at Q4_K_M GGUF using ~14 GB of ~48 GB usable.

- Model: 20B MMDIT image model, peak ~14 GB VRAM at Q4_K_M GGUF
- Device: 64 GB unified, ~48 GB usable
- All components resident (no offload): ~57 GB
- Offload floor (slow): ~3 GB
- Tools: ComfyUI, Nunchaku (SVDQuant 4-bit)
- License: Apache-2.0 (commercial use: yes)

Sources: https://huggingface.co/Qwen/Qwen-Image, https://huggingface.co/city96/Qwen-Image-gguf, https://docs.comfy.org/tutorials/image/qwen/qwen-image, https://sandner.art/qwen-image-and-edit-local-gguf-generations-with-lightning/, https://github.com/QwenLM/Qwen-Image.

More: https://localmodel.run/can-i-run/qwen-image/apple-m4-max-64gb