FA

FastH3 Omni GGUFs

FastvideoGGUF by realrebelaiUpdated 2026-10-23
Download on Hugging Face
Parameters22.1B
Context—
Layers—
Architecturewan
Smallest quant8.5 GB
Quick answer

FastH3 Omni GGUFs needs about 16.0 GB of memory at Q4_K_M (a 13.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 5 quants, from 8.5 GB (Q2_K) to 14.6 GB (Q4_K_M).

FastH3 Omni GGUFs – 22.1B parameter video‑audio generation

FastH3 Omni is a 22.1B parameter reference‑conditioned model that generates video with synchronized audio from text and ordered image, video, and audio references. It uses eight transformer evaluations and guidance 1.0. The GGUF files are quantized versions of the BF16 reference transformer.

Good at

  • Video and audio generation from text and references
  • Reference‑conditioned output
  • 8‑step distilled architecture

Limits

  • No vision support in the GGUF files
  • Requires a compatible GGUF diffusion‑model loader
  • License is other, not open source

Best for

  • Generating short video clips with audio
  • Creating reference‑conditioned media assets
  • Testing ComfyUI diffusion pipelines

Who it’s for. Developers and researchers who need a reference‑conditioned video‑audio model for experimentation. The model is suitable for local inference on GPUs with sufficient VRAM and for server deployment with UniServe or similar runtimes.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K8.5 GB 10.0 GB
Too big Get file →
Q2_K8.9 GB 10.4 GB
Too big Get file →
Q3_K_S11.0 GB 12.8 GB
Too big Get file →
Q4_K_M13.8 GB 16.0 GB
Too big Get file →
Q4_K_M14.6 GB 16.8 GB
Too big Get file →

For 8‑GB VRAM, use the Q2_K quantization (8.49 GB file, ~10 GB memory at 8k context). For 12‑GB VRAM, use Q3_K_S (11.03 GB file, ~12.8 GB memory). For 16‑GB VRAM, use Q4_K_M (13.84 GB file, ~16 GB memory). Memory estimates are approximate.

What GPU do you need for FastH3 Omni GGUFs?

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 Q2_K (8.9 GB file, about 10.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (13.8 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (14.6 GB file, about 16.8 GB in use).

Which FastH3 Omni GGUFs quant should you choose?

Q4_K_M is the usual starting point for FastH3 Omni GGUFs: it balances file size and quality well. Here it is a 13.8 GB file.

If memory is tight, the smallest file is Q2_K at 8.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturewan
Parameters22.1B

Source

Quantized byrealrebelai
FamilyFastvideo
Licenseother
Downloads (HF)5,803
Last updated2026-10-23

Frequently asked questions about FastH3 Omni GGUFs

How much VRAM does FastH3 Omni GGUFs need?

About 16.0 GB at Q4_K_M with an 8K context window. That is the 13.8 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 FastH3 Omni GGUFs on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of FastH3 Omni GGUFs GGUF?

It depends on the quant: Q2_K is 8.5 GB, Q2_K is 8.9 GB, Q3_K_S is 11.0 GB, Q4_K_M is 13.8 GB, Q4_K_M is 14.6 GB.

Where can I download FastH3 Omni GGUFs GGUF?

The files are on Hugging Face in the realrebelai/FastH3-Omni_GGUFs repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does FastH3 Omni GGUFs use?

Hugging Face lists the license as other. 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 FastH3 Omni on 8 GB VRAM?

Yes, the Q2_K quantization file is 8.49 GB and requires about 10 GB of VRAM at 8k context, which fits an 8 GB GPU with some overhead.

Does the model support vision inputs?

No, the GGUF files do not include vision support; they are reference‑conditioned only.

What runtime is recommended for local inference?

Use a GGUF diffusion‑model loader such as ComfyUI or llama.cpp with the appropriate quantization for your GPU.

Similar models

Browse all →

More from realrebelai

All by realrebelai →

More Fastvideo models

All Fastvideo →

Other medium models

All medium models →