WanVideo comfy needs about 2.1 GB of memory at Q4_K_M (a 1.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 14 quants, from 1.4 GB (Q4_K_M) to 19.4 GB (Q8_0).
WanVideo comfy – a 2.49B parameter video dubbing model
WanVideo comfy is a 2.49B parameter model derived from InfiniteTalk. It is designed for sparse‑frame video dubbing with accurate lip, head, body, and expression synchronization. The model is released under the Apache‑2.0 license.
Good at
- Accurate lip synchronization
- Infinite‑length video generation
- Stable head and body motion
Limits
- No vision support in this GGUF variant
- Requires 8‑k context for estimates
- Large memory for higher quants
Best for
- Video dubbing with audio input
- Image‑audio to video synthesis
- Custom ComfyUI workflows
Who it’s for. Developers and researchers building audio‑driven video generation tools. The model is suitable for integration into ComfyUI pipelines and other llama.cpp compatible frameworks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.4 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_M | 1.4 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_M | 2.0 GB | 2.7 GB | Fits | Get file → | |
| Q4_K_M | 2.0 GB | 2.7 GB | Fits | Get file → | |
| Q4_K_M | 2.0 GB | 2.7 GB | Fits | Get file → | |
| Q6_K | 2.0 GB | 2.8 GB | Fits | Get file → | |
| Q6_K | 2.0 GB | 2.8 GB | Fits | Get file → | |
| — | 2.6 GB | 3.5 GB | Fits | Get file → | |
| — | 2.6 GB | 3.5 GB | Fits | Get file → | |
| Q8_0 | 3.2 GB | 4.1 GB | Fits | Get file → | |
| Q8_0 | 3.2 GB | 4.1 GB | Fits | Get file → | |
| Q8_0 | 3.2 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_M | 12.6 GB | 14.6 GB | Too big | Get file → | |
| Q8_0 | 19.4 GB | 22.3 GB | Too big | Get file → |
For 8‑GB VRAM, use the Q4_K_M quant (1.4 GB file, ~2.1 GB memory). If 12‑GB VRAM is available, Q6_K (2.04 GB file, ~2.8 GB memory) offers higher quality. For best quality and ample memory, Q8_0 (3.25 GB file, ~4.1 GB memory) is recommended.
What GPU do you need for WanVideo comfy?
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 the main file (2.6 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 4.1 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 4.1 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 4.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (12.6 GB file, about 14.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (19.4 GB file, about 22.3 GB in use).
Which WanVideo comfy quant should you choose?
Q4_K_M is the usual starting point for WanVideo comfy: it balances file size and quality well. Here it is a 1.4 GB file.
The Q8_0 file is 3.2 GB, about 2.3 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about WanVideo comfy
How much VRAM does WanVideo comfy need?
About 2.1 GB at Q4_K_M with an 8K context window. That is the 1.4 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 WanVideo comfy on an 8 GB GPU?
Yes, with Q8_0: the 3.2 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of WanVideo comfy GGUF?
It depends on the quant: Q4_K_M is 1.4 GB, Q4_K_M is 1.4 GB, Q4_K_M is 2.0 GB, Q4_K_M is 2.0 GB, Q4_K_M is 2.0 GB, Q6_K is 2.0 GB and 8 more.
Where can I download WanVideo comfy GGUF?
The files are on Hugging Face in the Kijai/WanVideo_comfy_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 WanVideo comfy 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 WanVideo comfy on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 2.1 GB memory at 8‑k context, fitting within 8 GB VRAM.
Does this model support vision input?
No, the provided GGUF files are for audio‑driven video generation only.
What license applies to this model?
The model is released under the Apache‑2.0 license.