Wan2.1 T2V 14B CausVid needs about 10.3 GB of memory at Q4_K_S (a 8.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 7.2 GB (Q3_K_M) to 10.3 GB (Q5_0).
Wan2.1 T2V 14B CausVid is a 14.3B-parameter Wan model in GGUF format, quantized by Njbx. The repository has 3 quant files, from 7.2 GB (Q3_K_M) to 10.3 GB (Q5_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 7.2 GB | 8.5 GB | Too big | Get file → | |
| Q4_K_S | 8.8 GB | 10.3 GB | Too big | Get file → | |
| Q5_0 | 10.3 GB | 12.1 GB | Too big | Get file → |
What GPU do you need for Wan2.1 T2V 14B CausVid?
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: the best quant that fits is Q4_K_S (8.8 GB file, about 10.3 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_0 (10.3 GB file, about 12.1 GB in use).
Which Wan2.1 T2V 14B CausVid quant should you choose?
Q4_K_S (8.8 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q3_K_M at 7.2 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Wan2.1 T2V 14B CausVid
How much VRAM does Wan2.1 T2V 14B CausVid need?
About 10.3 GB at Q4_K_S with an 8K context window. That is the 8.8 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 Wan2.1 T2V 14B CausVid on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Wan2.1 T2V 14B CausVid GGUF?
It depends on the quant: Q3_K_M is 7.2 GB, Q4_K_S is 8.8 GB, Q5_0 is 10.3 GB.
Where can I download Wan2.1 T2V 14B CausVid GGUF?
The files are on Hugging Face in the Njbx/Wan2.1-T2V-14B-CausVid-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Wan2.1 T2V 14B CausVid use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.