WA

Wan2.2 Custom Models

WanGGUF by tanishqwUpdated 2026-07-07
Download on Hugging Face
Parameters14.3B
Context—
Layers—
Architecturewan
Smallest quant9.7 GB
Quick answer

Wan2.2 Custom Models needs about 13.9 GB of memory at its main file (a 12.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 10 quants, from 9.7 GB to 15.4 GB.

Wan2.2 Custom Models is a 14.3B-parameter Wan model in GGUF format, quantized by tanishqw. The repository has 10 quant files, from 9.7 GB to 15.4 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—9.7 GB 11.3 GB
Too big Get file →
—9.7 GB 11.3 GB
Too big Get file →
—9.7 GB 11.3 GB
Too big Get file →
—9.7 GB 11.3 GB
Too big Get file →
—12.0 GB 13.9 GB
Too big Get file →
Q6_K12.0 GB 13.9 GB
Too big Get file →
—12.0 GB 13.9 GB
Too big Get file →
Q6_K12.0 GB 13.9 GB
Too big Get file →
—15.4 GB 17.8 GB
Too big Get file →
—15.4 GB 17.8 GB
Too big Get file →

What GPU do you need for Wan2.2 Custom Models?

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 the main file (9.7 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (12.0 GB file, about 13.9 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (15.4 GB file, about 17.8 GB in use).

Which Wan2.2 Custom Models quant should you choose?

If memory is tight, the smallest file is the first one in the table at 9.7 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturewan
Parameters14.3B

Source

Quantized bytanishqw
FamilyWan
Licenseapache-2.0
Downloads (HF)233
Last updated2026-07-07

Frequently asked questions about Wan2.2 Custom Models

How much VRAM does Wan2.2 Custom Models need?

About 13.9 GB at its main file with an 8K context window. That is the 12.0 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 Wan2.2 Custom Models on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Wan2.2 Custom Models GGUF?

It depends on the quant: file is 9.7 GB, file is 9.7 GB, file is 9.7 GB, file is 9.7 GB, file is 12.0 GB, Q6_K is 12.0 GB and 4 more.

Where can I download Wan2.2 Custom Models GGUF?

The files are on Hugging Face in the tanishqw/Wan2.2-Custom-Models-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 Wan2.2 Custom Models 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.

Similar models

Browse all →

More Wan models

All Wan →

Other medium models

All medium models →