# Can I run Wan 2.2 T2V A14B on Nvidia GeForce RTX 5090 (32GB)?

Updated: 2026-06-15

**Yes, it runs.** Runs at Q4 GGUF using ~16 GB of ~31 GB usable.

- Model: 27B DIT video model, peak ~16 GB VRAM at Q4 GGUF
- Device: 32 GB vram, ~31 GB usable
- All components resident (no offload): ~80 GB
- Offload floor (slow): ~8 GB
- Tools: ComfyUI, Diffusers
- License: Apache-2.0 (commercial use: yes)

Sources: https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B, https://huggingface.co/QuantStack/Wan2.2-T2V-A14B-GGUF, https://github.com/Wan-Video/Wan2.2.

More: https://localmodel.run/can-i-run/wan-2-2-t2v-a14b/nvidia-rtx-5090-32gb