WA

wan2.2

WanGGUF by tg159357Updated 2026-01-15
Download on Hugging Face
Parameters14.3B
Context512
Layers24
Architecturet5encoder
Smallest quant3.5 GB
Quick answer

wan2.2 needs about 12.5 GB of memory at Q4_K_S (a 8.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 5 quants, from 3.5 GB (Q4_K_S) to 8.7 GB (Q4_K_S).

wan2.2 is a 14.3B-parameter Wan model in GGUF format, quantized by tg159357. Its trained context length is 512 tokens. The repository has 5 quant files, from 3.5 GB (Q4_K_S) to 8.7 GB (Q4_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S3.5 GB 4.2 GB
Fits Get file →
Q4_K_S8.7 GB 9.4 GB
Too big Get file →
Q4_K_S8.7 GB 9.4 GB
Too big Get file →
Q4_K_S8.7 GB 9.4 GB
Too big Get file →
Q4_K_S8.7 GB 9.4 GB
Too big Get file →

What GPU do you need for wan2.2?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: the best quant that fits is Q4_K_S (3.5 GB file, about 7.2 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_S (3.5 GB file, about 7.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (8.7 GB file, about 12.5 GB in use).

Which wan2.2 quant should you choose?

Q4_K_S (8.7 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 Q4_K_S at 3.5 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturet5encoder
Parameters14.3B
Layers24
Trained context512 tokens
KV cache (fp16)384 KB per token

Source

Quantized bytg159357
FamilyWan
Repositorytg159357/wan2.2
Downloads (HF)9
Last updated2026-01-15

Frequently asked questions about wan2.2

How much VRAM does wan2.2 need?

About 12.5 GB at Q4_K_S with an 8K context window. That is the 8.7 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 on an 8 GB GPU?

Yes, with Q4_K_S: the 3.5 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of wan2.2 GGUF?

It depends on the quant: Q4_K_S is 3.5 GB, Q4_K_S is 8.7 GB, Q4_K_S is 8.7 GB, Q4_K_S is 8.7 GB, Q4_K_S is 8.7 GB.

What context length does wan2.2 support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 3.2 GB at 8K and 0.2 GB at 512.

Where can I download wan2.2 GGUF?

The files are on Hugging Face in the tg159357/wan2.2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from tg159357

All by tg159357 →

More Wan models

All Wan →

Other medium models

All medium models →