WA

LiveAvatar

WanGGUF by audio-cppUpdated 2026-09-18
Download on Hugging Face
Parameters16.3B
Context—
Layers—
Architectureliveavatar
Smallest quant0.3 GB
Quick answer

LiveAvatar needs about 5.1 GB of memory at Q4_K_S (a 4.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 0.3 GB (F16) to 13.9 GB.

Audio‑driven avatar video generation from image, speech, and text

LiveAvatar is a GGUF model based on Wan‑2.2‑S2V‑14B. It generates cinematic avatar videos from a reference image, speech audio, and a text prompt. The model is released under Apache‑2.0 and supports low‑VRAM mode for 720p generation.

Good at

  • Audio‑driven avatar creation
  • Cinematic‑level video generation
  • Text‑guided animation

Limits

  • No vision support beyond reference image
  • Requires all three GGUF files
  • Low‑VRAM mode adds host‑to‑device transfer overhead

Best for

  • Creating short avatar clips for social media
  • Generating lip‑sync video for podcasts
  • Producing character animation for indie games

Who it’s for. Developers and content creators who need realistic avatar videos from audio and text. The model is suitable for projects that can accommodate the 16.3 billion‑parameter size and the required memory footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.3 GB 0.8 GB
Fits Get file →
Q4_K_S4.1 GB 5.1 GB
Fits Get file →
—13.9 GB 16.0 GB
Too big Get file →

For 8 GB VRAM, use the Q4_K_S quant (4.13 GB file, ~5.1 GB memory at 8 k context). For 16 GB VRAM, the F16 quant (0.25 GB file, ~0.8 GB memory) is ideal. The unknown quant is large and not recommended for limited VRAM setups.

What GPU do you need for LiveAvatar?

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: the best quant that fits is F16 (0.3 GB file, about 0.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_S (4.1 GB file, about 5.1 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_S (4.1 GB file, about 5.1 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_S (4.1 GB file, about 5.1 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (13.9 GB file, about 16.0 GB in use).

Which LiveAvatar quant should you choose?

Q4_K_S (4.1 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 F16 at 0.3 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureliveavatar
Parameters16.3B

Source

Quantized byaudio-cpp
FamilyWan
Licenseapache-2.0
Downloads (HF)95,636
Last updated2026-09-18

Frequently asked questions about LiveAvatar

How much VRAM does LiveAvatar need?

About 5.1 GB at Q4_K_S with an 8K context window. That is the 4.1 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 LiveAvatar on an 8 GB GPU?

Yes, with Q4_K_S: the 4.1 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LiveAvatar GGUF?

It depends on the quant: F16 is 0.3 GB, Q4_K_S is 4.1 GB, file is 13.9 GB.

Where can I download LiveAvatar GGUF?

The files are on Hugging Face in the audio-cpp/LiveAvatar-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 LiveAvatar 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 LiveAvatar on 8 GB VRAM?

Yes, using the Q4_K_S quant will fit within 8 GB VRAM with an estimated 5.1 GB usage at 8 k context.

Do I need a GPU to run LiveAvatar?

LiveAvatar requires a GPU for inference; CPU execution is not supported.

What is the maximum resolution I can generate?

Low‑VRAM mode supports 720p generation near a 16 GiB VRAM limit, while higher resolutions need more VRAM.

Other GGUFs of Wan2.2-S2V-14B

Similar models

Browse all →

More from audio-cpp

All by audio-cpp →

More Wan models

All Wan →

Other medium models

All medium models →