Wan 2.1 needs about 20.8 GB of memory at Q8_0 (a 18.1 GB file) with an 8K context window, so it fits on a 24 GB GPU.
Wan 2.1 is a 16.4B-parameter Wan model in GGUF format, quantized by zer0991. The repository has 1 quant file, from 18.1 GB (Q8_0) to 18.1 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 18.1 GB | 20.8 GB | Too big | Get file → |
What GPU do you need for Wan 2.1?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q8_0 (18.1 GB file, about 20.8 GB in use).
Which Wan 2.1 quant should you choose?
Q8_0 (18.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Wan 2.1
How much VRAM does Wan 2.1 need?
About 20.8 GB at Q8_0 with an 8K context window. That is the 18.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Wan 2.1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Wan 2.1 GGUF?
It depends on the quant: Q8_0 is 18.1 GB.
Where can I download Wan 2.1 GGUF?
The files are on Hugging Face in the zer0991/Wan_2.1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Wan 2.1 use?
Hugging Face lists the license as unknown. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.