SK

SkyReels V3 14B

SkyreelsGGUF by vantagewithaiUpdated 2026-02-13
Download on Hugging Face
Parameters18.9B
Context—
Layers—
Architecturewan
Smallest quant5.8 GB
Quick answer

SkyReels V3 14B needs about 11.8 GB of memory at Q4_K_M (a 10.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 39 quants, from 5.8 GB (Q2_K) to 20.8 GB (Q8_0).

SkyReels V3 14B – multimodal video generation model

SkyReels V3 14B is a 18.9 billion‑parameter model built on a unified multimodal in‑context learning framework. It supports multi‑subject video generation from reference images, audio‑guided video creation, and video‑to‑video synthesis. The model is available in multiple GGUF quantizations.

Good at

  • Video generation from images
  • Audio‑guided video creation
  • Video‑to‑video synthesis

Limits

  • No vision support in text‑only contexts
  • Requires large VRAM for higher quants
  • License is other, not standard

Best for

  • Creating short video clips from stills
  • Generating audio‑driven video content
  • Extending existing videos with new frames

Who it’s for. Developers and researchers needing a versatile video generation model. The model is suitable for building applications that generate or extend video content from images or audio prompts.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.8 GB 7.0 GB
Fits Get file →
Q2_K5.8 GB 7.0 GB
Fits Get file →
Q3_K_S7.0 GB 8.3 GB
Too big Get file →
Q3_K_S7.0 GB 8.3 GB
Too big Get file →
Q2_K7.3 GB 8.7 GB
Too big Get file →
Q3_K_M7.6 GB 9.1 GB
Too big Get file →
Q3_K_M7.6 GB 9.1 GB
Too big Get file →
Q3_K_S9.0 GB 10.6 GB
Too big Get file →
Q4_09.0 GB 10.6 GB
Too big Get file →
Q4_09.0 GB 10.6 GB
Too big Get file →
Q4_K_S9.2 GB 10.8 GB
Too big Get file →
Q4_K_S9.2 GB 10.8 GB
Too big Get file →
Q3_K_M9.7 GB 11.3 GB
Too big Get file →
Q4_19.7 GB 11.4 GB
Too big Get file →
Q4_19.7 GB 11.4 GB
Too big Get file →
Q4_K_M10.1 GB 11.8 GB
Too big Get file →
Q4_K_M10.1 GB 11.8 GB
Too big Get file →
Q5_K_S10.6 GB 12.4 GB
Too big Get file →
Q5_K_S10.6 GB 12.4 GB
Too big Get file →
Q5_010.8 GB 12.6 GB
Too big Get file →
Q5_010.8 GB 12.6 GB
Too big Get file →
Q5_K_M11.3 GB 13.1 GB
Too big Get file →
Q5_K_M11.3 GB 13.1 GB
Too big Get file →
Q5_111.5 GB 13.4 GB
Too big Get file →
Q5_111.5 GB 13.4 GB
Too big Get file →
Q4_011.7 GB 13.5 GB
Too big Get file →
Q4_K_S11.8 GB 13.8 GB
Too big Get file →
Q6_K12.5 GB 14.5 GB
Too big Get file →
Q6_K12.5 GB 14.5 GB
Too big Get file →
Q4_112.6 GB 14.7 GB
Too big Get file →
Q4_K_M12.7 GB 14.8 GB
Too big Get file →
Q5_K_S13.8 GB 16.0 GB
Too big Get file →
Q5_014.0 GB 16.2 GB
Too big Get file →
Q5_K_M14.5 GB 16.7 GB
Too big Get file →
Q5_115.0 GB 17.3 GB
Too big Get file →
Q8_015.9 GB 18.3 GB
Too big Get file →
Q8_015.9 GB 18.3 GB
Too big Get file →
Q6_K16.3 GB 18.7 GB
Too big Get file →
Q8_020.8 GB 23.8 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (file size 5.77 GB, memory 7 GB at 8k context). For 12 GB VRAM, Q4_0 (file size 9.03 GB, memory 10.6 GB). For 16 GB VRAM, Q5_K_S (file size 10.61 GB, memory 12.4 GB). Estimates are approximate.

What GPU do you need for SkyReels V3 14B?

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: the best quant that fits is Q2_K (5.8 GB file, about 7.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (10.1 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_S (13.8 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (20.8 GB file, about 23.8 GB in use).

Which SkyReels V3 14B quant should you choose?

Q4_K_M is the usual starting point for SkyReels V3 14B: it balances file size and quality well. Here it is a 10.1 GB file.

The Q8_0 file is 15.9 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 Q2_K at 5.8 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
Parameters18.9B

Source

Quantized byvantagewithai
FamilySkyreels
Licenseother
Downloads (HF)1,107
Last updated2026-02-13

Frequently asked questions about SkyReels V3 14B

How much VRAM does SkyReels V3 14B need?

About 11.8 GB at Q4_K_M with an 8K context window. That is the 10.1 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 SkyReels V3 14B on an 8 GB GPU?

Yes, with Q2_K: the 5.8 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SkyReels V3 14B GGUF?

It depends on the quant: Q2_K is 5.8 GB, Q2_K is 5.8 GB, Q3_K_S is 7.0 GB, Q3_K_S is 7.0 GB, Q2_K is 7.3 GB, Q3_K_M is 7.6 GB and 33 more.

Where can I download SkyReels V3 14B GGUF?

The files are on Hugging Face in the vantagewithai/SkyReels-V3-14B-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 SkyReels V3 14B 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 SkyReels V3 on 8 GB VRAM?

Yes, the Q2_K quantization requires about 7 GB of VRAM at 8k context, which fits within an 8 GB budget.

Does the model support text‑only inference?

No, SkyReels V3 is a multimodal model and requires visual or audio inputs for generation.

What is the largest quantization available?

The largest available quantization is Q8_0 with a file size of 20.79 GB and an estimated memory of 23.8 GB at 8k context.

Similar models

Browse all →

More from vantagewithai

All by vantagewithai →

More Skyreels models

All Skyreels →

Other medium models

All medium models →