WA

WAN 2.2 Loras

WanGGUF by aktrm123asUpdated 2026-09-09
Download on Hugging Face
Parameters5.68B
Context512
Layers24
Architecturet5encoder
Smallest quant4.1 GB
Quick answer

WAN 2.2 Loras needs about 19.1 GB of memory at Q8_0 (a 15.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 4.1 GB (Q5_K_S) to 15.4 GB (Q8_0).

WAN 2.2 Loras is a 5.68B-parameter Wan model in GGUF format, quantized by aktrm123as. Its trained context length is 512 tokens. The repository has 3 quant files, from 4.1 GB (Q5_K_S) to 15.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S4.1 GB 4.8 GB
Fits Get file →
Q8_015.4 GB 16.1 GB
Too big Get file →
Q8_015.4 GB 16.1 GB
Too big Get file →

What GPU do you need for WAN 2.2 Loras?

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 Q5_K_S (4.1 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_S (4.1 GB file, about 7.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_S (4.1 GB file, about 7.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.4 GB file, about 19.1 GB in use).

Which WAN 2.2 Loras quant should you choose?

Q8_0 (15.4 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.

If memory is tight, the smallest file is Q5_K_S at 4.1 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturet5encoder
Parameters5.68B
Layers24
Trained context512 tokens
KV cache (fp16)384 KB per token

Source

Quantized byaktrm123as
FamilyWan
Downloads (HF)178
Last updated2026-09-09

Frequently asked questions about WAN 2.2 Loras

How much VRAM does WAN 2.2 Loras need?

About 19.1 GB at Q8_0 with an 8K context window. That is the 15.4 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 2.2 Loras on an 8 GB GPU?

Yes, with Q5_K_S: the 4.1 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of WAN 2.2 Loras GGUF?

It depends on the quant: Q5_K_S is 4.1 GB, Q8_0 is 15.4 GB, Q8_0 is 15.4 GB.

What context length does WAN 2.2 Loras 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 WAN 2.2 Loras GGUF?

The files are on Hugging Face in the aktrm123as/WAN_2.2_Loras 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 Wan models

All Wan →

Other small models

All small models →