WA

SteadyDancer

WanGGUF by MCG-NJUUpdated 2025-12-08
Download on Hugging Face
Parameters16.4B
Context—
Layers—
Architecturewan
Smallest quant10.0 GB
Quick answer

SteadyDancer needs about 12.7 GB of memory at Q4_K_M (a 10.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 10 quants, from 10.0 GB (Q4_K_S) to 13.7 GB (Q6_K).

SteadyDancer: 16.4B parameter video animation model

SteadyDancer is a 16.4B parameter model for human image animation with first‑frame preservation. It is a GGUF checkpoint derived from Wan2.1 I2V‑14B. The model supports text‑to‑video, image‑to‑video, and video editing tasks.

Good at

  • Human image animation
  • First‑frame preservation
  • Coherent motion generation

Limits

  • No vision support in GGUF
  • Requires large VRAM for full precision
  • License is Apache‑2.0

Best for

  • Animating still portraits
  • Creating short video clips from images
  • Editing motion in existing videos

Who it’s for. Researchers and developers needing high‑quality human animation from static images. The model is suitable for integration into pipelines that support GGUF and llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S10.0 GB 11.6 GB
Too big Get file →
Q4_K_S10.0 GB 11.6 GB
Too big Get file →
Q4_K_M10.9 GB 12.7 GB
Too big Get file →
Q4_K_M10.9 GB 12.7 GB
Too big Get file →
Q5_K_S11.6 GB 13.5 GB
Too big Get file →
Q5_K_S11.6 GB 13.5 GB
Too big Get file →
Q5_K_M12.3 GB 14.2 GB
Too big Get file →
Q5_K_M12.3 GB 14.2 GB
Too big Get file →
Q6_K13.7 GB 15.9 GB
Too big Get file →
Q6_K13.7 GB 15.9 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (9.95 GB file, ~11.6 GB memory at 8k context). For 12 GB VRAM, Q4_K_M (10.86 GB file, ~12.7 GB memory). For 16 GB VRAM, Q5_K_M (12.26 GB file, ~14.2 GB memory).

What GPU do you need for SteadyDancer?

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 (10.0 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (13.7 GB file, about 15.9 GB in use).

Which SteadyDancer quant should you choose?

Q4_K_M is the usual starting point for SteadyDancer: it balances file size and quality well. Here it is a 10.9 GB file.

If memory is tight, the smallest file is Q4_K_S at 10.0 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

Architecturewan
Parameters16.4B

Source

Quantized byMCG-NJU
FamilyWan
Licenseapache-2.0
Downloads (HF)1,499
Last updated2025-12-08

Frequently asked questions about SteadyDancer

How much VRAM does SteadyDancer need?

About 12.7 GB at Q4_K_M with an 8K context window. That is the 10.9 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 SteadyDancer on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SteadyDancer GGUF?

It depends on the quant: Q4_K_S is 10.0 GB, Q4_K_S is 10.0 GB, Q4_K_M is 10.9 GB, Q4_K_M is 10.9 GB, Q5_K_S is 11.6 GB, Q5_K_S is 11.6 GB and 4 more.

Where can I download SteadyDancer GGUF?

The files are on Hugging Face in the MCG-NJU/SteadyDancer-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 SteadyDancer 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.

Can I run SteadyDancer on an RTX 3060 with 12 GB VRAM?

Yes, using Q4_K_M or Q5_K_S quantizations will fit within 12 GB VRAM, though memory usage is approximate.

Does the model support text prompts in multiple languages?

The model’s language support is not specified; only the base model is provided.

Is there a version with lower memory usage?

Lower memory versions use Q4_K_S quantization, which requires about 11.6 GB memory at 8k context.

Other GGUFs of Wan2.1-I2V-14B-480P

Similar models

Browse all →

More Wan models

All Wan →

Other medium models

All medium models →