FastHunyuan 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).
FastHunyuan – a 12.8B accelerated HunyuanVideo model
FastHunyuan is a 12.8B parameter model derived from FastVideo/FastHunyuan. It supports video generation with 6 diffusion steps, offering a speed increase over the original HunyuanVideo. The model is available in multiple GGUF quantizations.
Good at
- Video generation with 6 diffusion steps
- Fast inference on high‑end GPUs
- Compatibility with ComfyUI HunyuanVideo nodes
Limits
- No vision support beyond video generation
- Requires high VRAM for larger quantizations
- License is other, not open source
Best for
- Rapid video prototyping
- Low‑latency video inference
- Testing diffusion step reductions
Who it’s for. Developers and researchers needing faster video generation than HunyuanVideo. Suitable for environments with RTX4090‑class GPUs or higher. The model is intended for use with ComfyUI and native HunyuanVideo nodes.
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 (file size 6.09 GB, estimated 7.3 GB memory). For 16 GB VRAM, Q4_0 or Q4_K_S (7.74 GB, ~9.2 GB). For 24 GB VRAM, Q5_0 or Q5_K_S (9.3 GB, ~10.9 GB). Larger quantizations require more VRAM.
What GPU do you need for FastHunyuan?
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 FastHunyuan quant should you choose?
Q4_K_M is the usual starting point for FastHunyuan: 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 FastHunyuan
How much VRAM does FastHunyuan 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 FastHunyuan 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 FastHunyuan 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 FastHunyuan GGUF?
The files are on Hugging Face in the city96/FastHunyuan-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 FastHunyuan 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 FastHunyuan on 8 GB VRAM?
The smallest quantization Q3_K_S requires about 7.3 GB memory at 8 k context, so it can run on 8 GB VRAM with some headroom.
Does FastHunyuan support vision tasks other than video?
FastHunyuan is designed for video generation and does not support additional vision tasks.
What GPU is recommended for inference?
Inference is demonstrated on a single RTX4090, which can handle NF4 or LLM‑INT8 quantizations with 20 GB VRAM.