SC

SCAIL 2

ScailGGUF by AbirayUpdated 2026-06-14
Download on Hugging Face
Parameters16.4B
Context—
Layers—
Architecturewan
Smallest quant9.1 GB
Quick answer

SCAIL 2 needs about 13.3 GB of memory at Q4_K_M (a 11.5 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 7 quants, from 9.1 GB (Q3_K_M) to 18.1 GB (Q8_0).

SCAIL 2 – 16.4B parameter end‑to‑end controlled character animation model

SCAIL 2 is a 16.4B parameter model built on the Wan 2.1 architecture. It performs end‑to‑end controlled character animation and motion transfer without intermediate pose representations. The model supports cross‑identity replacement, animal driving, and zero‑shot advanced control intermediates.

Good at

  • End‑to‑end character animation
  • Cross‑identity replacement
  • Zero‑shot advanced control

Limits

  • No vision support in GGUF
  • Requires multiple external modules
  • Large VRAM for higher quantizations

Best for

  • Animating characters from driving videos
  • Multi‑character scenarios
  • Research on motion transfer

Who it’s for. Developers and researchers needing a unified motion transfer model for character animation. The model is open‑source under the MIT license and requires additional modules for full functionality.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M9.1 GB 10.7 GB
Too big Get file →
Q4_K_S10.7 GB 12.5 GB
Too big Get file →
Q4_K_M11.5 GB 13.3 GB
Too big Get file →
Q5_K_S12.1 GB 14.0 GB
Too big Get file →
Q5_K_M13.0 GB 15.0 GB
Too big Get file →
Q6_K14.2 GB 16.4 GB
Too big Get file →
Q8_018.1 GB 20.8 GB
Too big Get file →

For 8 GB VRAM, use Q3_K_M (file size 9.11 GB, estimated memory 10.7 GB). For 12 GB VRAM, Q4_K_S (10.68 GB, 12.5 GB) or Q4_K_M (11.46 GB, 13.3 GB). For 16 GB VRAM, Q5_K_S (12.09 GB, 14 GB) or Q5_K_M (12.97 GB, 15 GB). Higher quants need more VRAM.

What GPU do you need for SCAIL 2?

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 Q3_K_M (9.1 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (13.0 GB file, about 15.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (18.1 GB file, about 20.8 GB in use).

Which SCAIL 2 quant should you choose?

Q4_K_M is the usual starting point for SCAIL 2: it balances file size and quality well. Here it is a 11.5 GB file.

The Q8_0 file is 18.1 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_M at 9.1 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

Architecturewan
Parameters16.4B

Source

Quantized byAbiray
FamilyScail
Base modelzai-org/SCAIL-2
Licensemit
Downloads (HF)8,939
Last updated2026-06-14

Frequently asked questions about SCAIL 2

How much VRAM does SCAIL 2 need?

About 13.3 GB at Q4_K_M with an 8K context window. That is the 11.5 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 SCAIL 2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SCAIL 2 GGUF?

It depends on the quant: Q3_K_M is 9.1 GB, Q4_K_S is 10.7 GB, Q4_K_M is 11.5 GB, Q5_K_S is 12.1 GB, Q5_K_M is 13.0 GB, Q6_K is 14.2 GB and 1 more.

Where can I download SCAIL 2 GGUF?

The files are on Hugging Face in the Abiray/SCAIL-2-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 SCAIL 2 use?

Hugging Face lists the license as mit. 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 SCAIL 2 on 8 GB VRAM?

Use the Q3_K_M quantization; it requires about 10.7 GB of VRAM at 8k context.

Does the GGUF version include vision modules?

No, the GGUF weights are for the diffusion transformer only; vision modules must be added separately.

What license applies to SCAIL 2?

The model is released under the MIT license.

Other GGUFs of SCAIL-2

Similar models

Browse all →

More from Abiray

All by Abiray →

More Scail models

All Scail →

Other medium models

All medium models →