HunyuanVideo 1.5 T2V 720p needs about 6.2 GB of memory at Q4_K_M (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 4.9 GB (Q4_K_S) to 9.0 GB (Q8_0).
HunyuanVideo 1.5 T2V 720p – lightweight 8.33B parameter video generation
HunyuanVideo 1.5 T2V 720p is a video generation model with 8.33B parameters. It is quantized into multiple GGUF formats for efficient inference. The model runs smoothly on consumer‑grade GPUs and supports 720p output.
Good at
- Efficient 720p video generation
- Low‑parameter lightweight model
- Compatible with llama.cpp and ComfyUI-GGUF
Limits
- No vision support
- No explicit license details
- Context length not specified
Best for
- Short video creation
- Rapid prototyping
- Creative content generation
Who it’s for. Developers and creators needing fast 720p video generation on modest hardware. The model is suitable for those who prefer a lightweight alternative to larger video models.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_S | 4.9 GB | 6.0 GB | Fits | Get file → | |
| Q4_K_M | 5.1 GB | 6.2 GB | Fits | Get file → | |
| Q5_K_S | 5.9 GB | 7.2 GB | Fits | Get file → | |
| Q5_K_M | 6.1 GB | 7.4 GB | Tight | Get file → | |
| Q6_K | 7.0 GB | 8.4 GB | Too big | Get file → | |
| Q8_0 | 9.0 GB | 10.6 GB | Too big | Get file → |
For 8GB VRAM, use Q4_K_S (file size 4.92GB, estimated memory 6GB at 8k context). For 12GB VRAM, Q5_K_M (file size 6.12GB, estimated memory 7.4GB). For 16GB VRAM, Q6_K (file size 7.02GB, estimated memory 8.4GB).
What GPU do you need for HunyuanVideo 1.5 T2V 720p?
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: the best quant that fits is Q4_K_S (4.9 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (6.1 GB file, about 7.4 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.0 GB file, about 10.6 GB in use).
Which HunyuanVideo 1.5 T2V 720p quant should you choose?
Q4_K_M is the usual starting point for HunyuanVideo 1.5 T2V 720p: it balances file size and quality well. Here it is a 5.1 GB file.
The Q8_0 file is 9.0 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 Q4_K_S at 4.9 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about HunyuanVideo 1.5 T2V 720p
How much VRAM does HunyuanVideo 1.5 T2V 720p need?
About 6.2 GB at Q4_K_M with an 8K context window. That is the 5.1 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 HunyuanVideo 1.5 T2V 720p on an 8 GB GPU?
Yes, with Q5_K_M: the 6.1 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of HunyuanVideo 1.5 T2V 720p GGUF?
It depends on the quant: Q4_K_S is 4.9 GB, Q4_K_M is 5.1 GB, Q5_K_S is 5.9 GB, Q5_K_M is 6.1 GB, Q6_K is 7.0 GB, Q8_0 is 9.0 GB.
Where can I download HunyuanVideo 1.5 T2V 720p GGUF?
The files are on Hugging Face in the jayn7/HunyuanVideo-1.5_T2V_720p-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8GB VRAM?
Yes, the Q4_K_S quantization requires approximately 6GB of VRAM at 8k context, fitting within an 8GB GPU.
What is the smallest quantization available?
The smallest quantization is Q4_K_S with a file size of 4.92GB and estimated memory of 6GB at 8k context.
Does the model support FP16 inference?
The original model supports FP16, but the provided GGUF files are quantized; FP16 is not listed in the available quantizations.