hunyuan needs about 9.3 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 13 quants, from 6.1 GB (Q3_K_S) to 25.6 GB (BF16).
12.8B Hunyuan Video model for text‑to‑video generation
The Hunyuan Video model is a 12.8B parameter hybrid architecture designed for text‑to‑video tasks. It is available in multiple GGUF quantizations and can be used with ComfyUI workflows.
Good at
- Text‑to‑video generation
- Hybrid architecture support
- ComfyUI integration
Limits
- No vision support in GGUF
- Requires 8k context for estimates
- License type unknown
Best for
- Creating short video clips from prompts
- Testing video generation pipelines
- Prototyping hybrid models
Who it’s for. Developers and researchers working on text‑to‑video models who need a compact GGUF version for local inference. The model is suitable for those using ComfyUI and looking for a repackaged version of the original Hunyuan Video.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 6.1 GB | 7.3 GB | Tight | Get file → | |
| Q3_K_M | 6.2 GB | 7.5 GB | Tight | Get file → | |
| Q4_0 | 7.7 GB | 9.2 GB | Too big | Get file → | |
| Q4_K_S | 7.7 GB | 9.2 GB | Too big | Get file → | |
| Q4_K_M | 7.9 GB | 9.3 GB | Too big | Get file → | |
| Q4_1 | 8.5 GB | 10.0 GB | Too big | Get file → | |
| Q5_0 | 9.3 GB | 10.9 GB | Too big | Get file → | |
| Q5_K_S | 9.3 GB | 10.9 GB | Too big | Get file → | |
| Q5_K_M | 9.4 GB | 11.1 GB | Too big | Get file → | |
| Q5_1 | 10.1 GB | 11.8 GB | Too big | Get file → | |
| Q6_K | 11.0 GB | 12.8 GB | Too big | Get file → | |
| Q8_0 | 14.0 GB | 16.1 GB | Too big | Get file → | |
| BF16 | 25.6 GB | 29.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q3_K_S (6.09 GB) or Q3_K_M (6.24 GB). For 12 GB VRAM, Q4_K_M (7.88 GB) or Q5_K_M (9.45 GB) are suitable. Higher precision quants like Q8_0 (13.97 GB) require more memory and are best for systems with 16 GB+ VRAM.
What GPU do you need for hunyuan?
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 Q3_K_M (6.2 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_1 (10.1 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (11.0 GB file, about 12.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (14.0 GB file, about 16.1 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (25.6 GB file, about 29.2 GB in use).
Which hunyuan quant should you choose?
Q4_K_M is the usual starting point for hunyuan: it balances file size and quality well. Here it is a 7.9 GB file.
The Q8_0 file is 14.0 GB, about 1.8 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 Q3_K_S at 6.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about hunyuan
How much VRAM does hunyuan need?
About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.9 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 hunyuan on an 8 GB GPU?
Yes, with Q3_K_M: the 6.2 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of hunyuan GGUF?
It depends on the quant: Q3_K_S is 6.1 GB, Q3_K_M is 6.2 GB, Q4_0 is 7.7 GB, Q4_K_S is 7.7 GB, Q4_K_M is 7.9 GB, Q4_1 is 8.5 GB and 7 more.
Where can I download hunyuan GGUF?
The files are on Hugging Face in the calcuis/hunyuan-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 hunyuan 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 the model on 8 GB VRAM?
Yes, use Q3_K_S or Q3_K_M quantizations, which are 6.09 GB and 6.24 GB respectively.
Does the model support vision tasks?
The GGUF version does not include vision support.
Where can I find workflows for this model?
Workflows are available in the ComfyUI examples linked in the repo card.