wan s2v needs about 16.0 GB of memory at Q4_K_M (a 13.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 18 quants, from 0.6 GB (F16) to 32.8 GB (BF16).
Wan S2V: Audio‑driven cinematic video generation
Wan S2V is a 16.3 billion‑parameter model for generating cinematic video from audio. It builds on the Wan2.2 architecture and is available in multiple GGUF quantizations. The model is released under the Apache‑2.0 license.
Good at
- Audio‑driven cinematic video generation
- High‑fidelity lip‑sync editing
- Long‑form video creation
Limits
- No vision support beyond audio
- Requires large VRAM for higher‑quality quants
- No Mixture‑of‑Experts
Best for
- Creating cinematic character animations from speech
- Editing video lip‑sync for movies
- Generating long‑form audio‑driven videos
Who it’s for. Developers and researchers working on audio‑driven video synthesis. The model is suitable for projects that need cinematic‑level animation from audio input.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q2_K | 9.5 GB | 11.2 GB | Too big | Get file → | |
| IQ2_S | 9.7 GB | 11.3 GB | Too big | Get file → | |
| IQ3_XXS | 10.7 GB | 12.5 GB | Too big | Get file → | |
| IQ3_S | 12.0 GB | 13.9 GB | Too big | Get file → | |
| IQ4_XS | 12.2 GB | 14.1 GB | Too big | Get file → | |
| IQ4_NL | 12.6 GB | 14.6 GB | Too big | Get file → | |
| Q4_0 | 12.8 GB | 14.8 GB | Too big | Get file → | |
| Q4_K_S | 13.0 GB | 15.0 GB | Too big | Get file → | |
| Q4_1 | 13.5 GB | 15.6 GB | Too big | Get file → | |
| Q4_K_M | 13.9 GB | 16.0 GB | Too big | Get file → | |
| Q5_K_S | 14.3 GB | 16.6 GB | Too big | Get file → | |
| Q5_0 | 14.5 GB | 16.8 GB | Too big | Get file → | |
| Q5_K_M | 15.0 GB | 17.3 GB | Too big | Get file → | |
| Q5_1 | 15.2 GB | 17.6 GB | Too big | Get file → | |
| Q6_K | 16.2 GB | 18.7 GB | Too big | Get file → | |
| Q8_0 | 19.6 GB | 22.5 GB | Too big | Get file → | |
| BF16 | 32.8 GB | 37.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_S (file size 12.96 GB, estimated 15 GB memory). For 12 GB VRAM, Q4_K_M (13.86 GB, 16 GB memory). For 16 GB VRAM, Q5_K_M (15 GB, 17.3 GB memory). All estimates are approximate.
What GPU do you need for wan s2v?
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 (0.6 GB file, about 1.2 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (0.6 GB file, about 1.2 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (0.6 GB file, about 1.2 GB in use).
- 12 GB VRAM: the best quant that fits is IQ2_S (9.7 GB file, about 11.3 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (13.9 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (19.6 GB file, about 22.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (19.6 GB file, about 22.5 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (32.8 GB file, about 37.2 GB in use).
Which wan s2v quant should you choose?
Q4_K_M is the usual starting point for wan s2v: it balances file size and quality well. Here it is a 13.9 GB file.
The Q8_0 file is 19.6 GB, about 1.4 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 F16 at 0.6 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
Source
Frequently asked questions about wan s2v
How much VRAM does wan s2v need?
About 16.0 GB at Q4_K_M with an 8K context window. That is the 13.9 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 wan s2v on an 8 GB GPU?
Yes, with F16: the 0.6 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of wan s2v GGUF?
It depends on the quant: F16 is 0.6 GB, Q2_K is 9.5 GB, IQ2_S is 9.7 GB, IQ3_XXS is 10.7 GB, IQ3_S is 12.0 GB, IQ4_XS is 12.2 GB and 12 more.
Where can I download wan s2v GGUF?
The files are on Hugging Face in the calcuis/wan-s2v-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 wan s2v 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 Wan S2V on 8 GB VRAM?
Yes, using the Q4_K_S quantization which requires about 15 GB of VRAM at 8 k context.
Does Wan S2V support vision input?
No, the model is audio‑driven and does not process visual input.