ltxv 13b 0.9.7 dev needs about 10.4 GB of memory at Q4_K_M (a 8.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 5.9 GB (Q3_K_S) to 26.1 GB (F16).
13B LTX-Video model for image‑to‑video generation
ltxv 13b 0.9.7 dev is a diffusion‑based image‑to‑video model. It generates 30 FPS videos at 1216×704 resolution. The model is available in multiple GGUF quantizations for use with llama.cpp or ComfyUI.
Good at
- Real‑time 30 FPS video generation
- High‑resolution 1216×704 output
- English prompt driven control
Limits
- Requires 8 k context for memory estimates
- No vision support, only image‑to‑video
- License terms are other, not open source
Best for
- Creating short video clips from still images
- Testing diffusion video pipelines
- Generating training data for video models
Who it’s for. Developers and researchers needing a lightweight diffusion video model. The model is suitable for local inference on GPUs with sufficient VRAM and for integration into ComfyUI workflows.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 5.9 GB | 7.1 GB | Fits | Get file → | |
| Q3_K_M | 6.5 GB | 7.8 GB | Tight | Get file → | |
| Q4_0 | 7.8 GB | 9.2 GB | Too big | Get file → | |
| Q4_K_S | 8.0 GB | 9.4 GB | Too big | Get file → | |
| Q4_1 | 8.4 GB | 9.9 GB | Too big | Get file → | |
| Q4_K_M | 8.8 GB | 10.4 GB | Too big | Get file → | |
| Q5_K_S | 9.2 GB | 10.8 GB | Too big | Get file → | |
| Q5_0 | 9.4 GB | 11.0 GB | Too big | Get file → | |
| Q5_K_M | 9.8 GB | 11.5 GB | Too big | Get file → | |
| Q5_1 | 10.0 GB | 11.7 GB | Too big | Get file → | |
| Q6_K | 10.9 GB | 12.7 GB | Too big | Get file → | |
| Q8_0 | 14.0 GB | 16.2 GB | Too big | Get file → | |
| BF16 | 26.1 GB | 29.7 GB | Too big | Get file → | |
| F16 | 26.1 GB | 29.7 GB | Too big | Get file → |
For 8 GB VRAM use Q3_K_S (5.86 GB, ~7.1 GB memory). With 12 GB VRAM Q4_K_M (8.82 GB, ~10.4 GB memory) is suitable. For higher quality and more VRAM use Q5_K_M (9.82 GB, ~11.5 GB memory).
What GPU do you need for ltxv 13b 0.9.7 dev?
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 (6.5 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_1 (10.0 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (10.9 GB file, about 12.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (14.0 GB file, about 16.2 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (26.1 GB file, about 29.7 GB in use).
Which ltxv 13b 0.9.7 dev quant should you choose?
Q4_K_M is the usual starting point for ltxv 13b 0.9.7 dev: it balances file size and quality well. Here it is a 8.8 GB file.
The Q8_0 file is 14.0 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 Q3_K_S at 5.9 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 ltxv 13b 0.9.7 dev
How much VRAM does ltxv 13b 0.9.7 dev need?
About 10.4 GB at Q4_K_M with an 8K context window. That is the 8.8 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 ltxv 13b 0.9.7 dev on an 8 GB GPU?
Yes, with Q3_K_M: the 6.5 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ltxv 13b 0.9.7 dev GGUF?
It depends on the quant: Q3_K_S is 5.9 GB, Q3_K_M is 6.5 GB, Q4_0 is 7.8 GB, Q4_K_S is 8.0 GB, Q4_1 is 8.4 GB, Q4_K_M is 8.8 GB and 8 more.
Where can I download ltxv 13b 0.9.7 dev GGUF?
The files are on Hugging Face in the ThePun1sher/ltxv-13b-0.9.7-dev-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 ltxv 13b 0.9.7 dev 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 ltxv 13b 0.9.7 dev on 8 GB VRAM?
Yes, use the Q3_K_S quantization which requires about 7.1 GB of VRAM at 8 k context.
Does this model support image prompts in languages other than English?
The model is trained with English prompts; other languages are not supported.
Is the model compatible with ComfyUI?
Yes, the GGUF files can be used in ComfyUI with the ComfyUI‑GGUF node.