LTX Video 0.9.6 dev needs about 2.0 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 13 quants, from 0.9 GB (Q3_K_S) to 3.8 GB (BF16).
LTX Video 0.9.6 dev – 1.92B parameter diffusion video generation
LTX Video 0.9.6 dev is a diffusion‑based image‑to‑video model from Lightricks. It generates 30 FPS videos at 1216×704 resolution in real‑time. The model is available as a GGUF file and supports English prompts.
Good at
- Real‑time 30 FPS video generation
- High‑resolution 1216×704 output
- Diffusion‑based image‑to‑video workflow
Limits
- Requires 8 k context for memory estimates
- No vision support beyond image‑to‑video
- License terms apply as per original model
Best for
- Real‑time video creation for content creators
- Rapid prototyping of video sequences
- Testing diffusion video generation pipelines
Who it’s for. Developers and researchers working on diffusion‑based video generation. The model is suitable for those who need a lightweight, quantized version for local inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 0.9 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q4_0 | 1.2 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_S | 1.2 GB | 1.9 GB | Fits | Get file → | |
| Q4_1 | 1.3 GB | 1.9 GB | Fits | Get file → | |
| Q4_K_M | 1.3 GB | 2.0 GB | Fits | Get file → | |
| Q5_K_S | 1.4 GB | 2.0 GB | Fits | Get file → | |
| Q5_0 | 1.4 GB | 2.1 GB | Fits | Get file → | |
| Q5_K_M | 1.5 GB | 2.2 GB | Fits | Get file → | |
| Q5_1 | 1.5 GB | 2.2 GB | Fits | Get file → | |
| Q6_K | 1.6 GB | 2.3 GB | Fits | Get file → | |
| Q8_0 | 2.1 GB | 2.8 GB | Fits | Get file → | |
| BF16 | 3.8 GB | 4.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.33 GB file, ~2 GB memory). For 12 GB VRAM, Q5_K_M (1.48 GB file, ~2.2 GB memory). For 16 GB VRAM, Q6_K (1.63 GB file, ~2.3 GB memory). Memory estimates are approximate.
What GPU do you need for LTX Video 0.9.6 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: the best quant that fits is Q8_0 (2.1 GB file, about 2.8 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (3.8 GB file, about 4.8 GB in use).
Which LTX Video 0.9.6 dev quant should you choose?
Q4_K_M is the usual starting point for LTX Video 0.9.6 dev: it balances file size and quality well. Here it is a 1.3 GB file.
The Q8_0 file is 2.1 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 0.9 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 LTX Video 0.9.6 dev
How much VRAM does LTX Video 0.9.6 dev need?
About 2.0 GB at Q4_K_M with an 8K context window. That is the 1.3 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 LTX Video 0.9.6 dev on an 8 GB GPU?
Yes, with BF16: the 3.8 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LTX Video 0.9.6 dev GGUF?
It depends on the quant: Q3_K_S is 0.9 GB, Q3_K_M is 1.0 GB, Q4_0 is 1.2 GB, Q4_K_S is 1.2 GB, Q4_1 is 1.3 GB, Q4_K_M is 1.3 GB and 7 more.
Where can I download LTX Video 0.9.6 dev GGUF?
The files are on Hugging Face in the city96/LTX-Video-0.9.6-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 LTX Video 0.9.6 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 LTX Video 0.9.6 dev on 8 GB VRAM?
Yes, using the Q4_K_M quantized file which requires about 2 GB of VRAM at 8 k context.
Does the model support non‑English prompts?
The model is trained for English prompts; other languages are not supported.
What resolution can I generate?
Resolutions divisible by 32 and under 720×1280 are recommended for best performance.