VI

Viggle Animate pruned

ViggleGGUF by AbirayUpdated 2026-09-13
Download on Hugging Face
Parameters20.1B
Context—
Layers—
Architecturewan
Smallest quant8.9 GB
Quick answer

Viggle Animate pruned needs about 13.5 GB of memory at Q4_K_M (a 11.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 8.9 GB (Q3_K_M) to 16.7 GB (Q6_K).

Pruned Viggle-Animate model for video-to-video character replacement

Viggle Animate pruned is a 20.1B parameter model built on MiniMax-H3. It is quantized into four GGUF variants for use with GGUF-compatible inference environments. The model focuses on transferring character appearance into driving videos while preserving motion.

Good at

  • Video-to-video character replacement
  • Appearance transfer
  • Motion preservation

Limits

  • No vision support
  • No license details provided
  • No context length specified

Best for

  • Character replacement in video editing
  • Motion transfer in animation
  • Video post‑production workflows

Who it’s for. Developers and researchers working on video editing and animation who need a lightweight, quantized model for character appearance transfer. Suitable for environments that support GGUF and ComfyUI workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M8.9 GB 10.5 GB
Too big Get file →
Q4_K_M11.6 GB 13.5 GB
Too big Get file →
Q5_K_M14.1 GB 16.3 GB
Too big Get file →
Q6_K16.7 GB 19.3 GB
Too big Get file →

For 8‑GB VRAM, use Q3_K_M (file size 8.91 GB, estimated memory 10.5 GB). For 12‑GB VRAM, Q4_K_M (11.57 GB, 13.5 GB). For 16‑GB VRAM, Q5_K_M (14.08 GB, 16.3 GB). Higher precision requires more memory.

What GPU do you need for Viggle Animate pruned?

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 (8.9 GB file, about 10.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (11.6 GB file, about 13.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (16.7 GB file, about 19.3 GB in use).

Which Viggle Animate pruned quant should you choose?

Q4_K_M is the usual starting point for Viggle Animate pruned: it balances file size and quality well. Here it is a 11.6 GB file.

If memory is tight, the smallest file is Q3_K_M at 8.9 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
Parameters20.1B

Source

Quantized byAbiray
FamilyViggle
Downloads (HF)1,181
Last updated2026-09-13

Frequently asked questions about Viggle Animate pruned

How much VRAM does Viggle Animate pruned need?

About 13.5 GB at Q4_K_M with an 8K context window. That is the 11.6 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 Viggle Animate pruned on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Viggle Animate pruned GGUF?

It depends on the quant: Q3_K_M is 8.9 GB, Q4_K_M is 11.6 GB, Q5_K_M is 14.1 GB, Q6_K is 16.7 GB.

Where can I download Viggle Animate pruned GGUF?

The files are on Hugging Face in the Abiray/Viggle-Animate-pruned-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Q3_K_M on 8 GB VRAM?

Q3_K_M requires about 10.5 GB of memory at 8k context, so it will not fit on 8 GB VRAM. Use a smaller context or a lower‑precision quantization if memory is limited.

Is there a license for this model?

The model is derived from MiniMax-H3 and Viggle-Animate. Users should review the MiniMax H3 Community License and Viggle-Animate release terms before use.

Can I use this model in ComfyUI?

Yes, the GGUF files are intended for use with GGUF‑compatible ComfyUI workflows, including ComfyUI‑Viggle‑Animate‑H3 nodes.

Similar models

Browse all →

More from Abiray

All by Abiray →

Other medium models

All medium models →