ltxv0.9.7 needs about 10.7 GB of memory at Q4_K_M (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 36 quants, from 2.5 GB (F16) to 52.2 GB (F32).
13B LTX-Video model for image‑to‑video generation
LTX-Video is a diffusion‑based image‑to‑video model. It produces 30 FPS videos at 1216×704 resolution. The model is trained on a large‑scale video dataset.
Good at
- Real‑time video generation
- High‑resolution output
- English prompt support
Limits
- Requires 8K context for estimates
- Large memory for higher quants
- License terms not specified
Best for
- Creating short video clips from images
- Generating video content for demos
- Testing diffusion video models
Who it’s for. Developers and researchers working on diffusion‑based video generation. The model is suitable for those who need high‑quality, real‑time video synthesis from image prompts.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 2.5 GB | 3.3 GB | Fits | Get file → | |
| Q4_0 | 2.8 GB | 3.6 GB | Fits | Get file → | |
| Q2_K | 5.0 GB | 6.1 GB | Fits | Get file → | |
| Q2_K | 5.0 GB | 6.1 GB | Fits | Get file → | |
| Q3_K_S | 6.2 GB | 7.4 GB | Tight | Get file → | |
| Q3_K_S | 6.2 GB | 7.4 GB | Tight | Get file → | |
| Q3_K_M | 6.8 GB | 8.1 GB | Too big | Get file → | |
| Q3_K_M | 6.8 GB | 8.1 GB | Too big | Get file → | |
| Q3_K_L | 7.4 GB | 8.8 GB | Too big | Get file → | |
| Q3_K_L | 7.4 GB | 8.8 GB | Too big | Get file → | |
| Q4_0 | 8.1 GB | 9.5 GB | Too big | Get file → | |
| Q4_0 | 8.1 GB | 9.5 GB | Too big | Get file → | |
| Q4_K_S | 8.3 GB | 9.8 GB | Too big | Get file → | |
| Q4_K_S | 8.3 GB | 9.8 GB | Too big | Get file → | |
| Q4_1 | 8.7 GB | 10.2 GB | Too big | Get file → | |
| Q4_1 | 8.7 GB | 10.2 GB | Too big | Get file → | |
| Q4_K_M | 9.1 GB | 10.7 GB | Too big | Get file → | |
| Q4_K_M | 9.1 GB | 10.7 GB | Too big | Get file → | |
| Q5_K_S | 9.5 GB | 11.1 GB | Too big | Get file → | |
| Q5_K_S | 9.5 GB | 11.1 GB | Too big | Get file → | |
| Q5_0 | 9.7 GB | 11.4 GB | Too big | Get file → | |
| Q5_0 | 9.7 GB | 11.4 GB | Too big | Get file → | |
| Q5_K_M | 10.1 GB | 11.8 GB | Too big | Get file → | |
| Q5_K_M | 10.1 GB | 11.8 GB | Too big | Get file → | |
| Q5_1 | 10.3 GB | 12.0 GB | Too big | Get file → | |
| Q5_1 | 10.3 GB | 12.0 GB | Too big | Get file → | |
| Q6_K | 11.2 GB | 13.0 GB | Too big | Get file → | |
| Q6_K | 11.2 GB | 13.0 GB | Too big | Get file → | |
| Q8_0 | 14.3 GB | 16.5 GB | Too big | Get file → | |
| Q8_0 | 14.3 GB | 16.5 GB | Too big | Get file → | |
| BF16 | 26.4 GB | 30.1 GB | Too big | Get file → | |
| F16 | 26.4 GB | 30.1 GB | Too big | Get file → | |
| BF16 | 26.4 GB | 30.1 GB | Too big | Get file → | |
| F16 | 26.4 GB | 30.1 GB | Too big | Get file → | |
| F32 | 52.2 GB (2 parts) | 58.9 GB | Too big | Get file → | |
| F32 | 52.2 GB (2 parts) | 58.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 2.75 GB, memory 3.6 GB). For 16 GB VRAM, Q3_K_S (file size 6.17 GB, memory 7.4 GB) is a good balance. For 32 GB VRAM, Q4_K_M (file size 9.12 GB, memory 10.7 GB) offers higher precision.
What GPU do you need for ltxv0.9.7?
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 Q4_0 (2.8 GB file, about 3.6 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_0 (2.8 GB file, about 3.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K_S (6.2 GB file, about 7.4 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_1 (10.3 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (11.2 GB file, about 13.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (14.3 GB file, about 16.5 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (26.4 GB file, about 30.1 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (26.4 GB file, about 30.1 GB in use).
Which ltxv0.9.7 quant should you choose?
Q4_K_M is the usual starting point for ltxv0.9.7: it balances file size and quality well. Here it is a 9.1 GB file.
The Q8_0 file is 14.3 GB, about 1.6 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 2.5 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 ltxv0.9.7
How much VRAM does ltxv0.9.7 need?
About 10.7 GB at Q4_K_M with an 8K context window. That is the 9.1 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 ltxv0.9.7 on an 8 GB GPU?
Yes, with Q3_K_S: the 6.2 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 ltxv0.9.7 GGUF?
It depends on the quant: F16 is 2.5 GB, Q4_0 is 2.8 GB, Q2_K is 5.0 GB, Q2_K is 5.0 GB, Q3_K_S is 6.2 GB, Q3_K_S is 6.2 GB and 30 more.
Where can I download ltxv0.9.7 GGUF?
The files are on Hugging Face in the calcuis/ltxv0.9.7-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 ltxv0.9.7 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 ltxv0.9.7 on 8 GB VRAM?
Yes, the Q4_0 quant uses 3.6 GB memory at 8K context, fitting within 8 GB VRAM.
What is the memory requirement for the full F32 quant?
The F32 quant is 52.17 GB file size and requires 58.9 GB memory at 8K context.
Does the model support vision input?
The model is image‑to‑video; it accepts image prompts but does not process arbitrary vision inputs beyond the image.