LTX 2.3 backup needs about 15.0 GB of memory at Q4_K_M (a 13.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 13.0 GB (Q4_K_M) to 20.6 GB (Q8_0).
LTX 2.3 backup – 19B parameter audio‑video diffusion model
LTX 2.3 backup is a 19B parameter diffusion model for generating synchronized audio and video. It is a direct backup of the LTX‑2 model and can be run locally using llama.cpp. The model is available in three quantizations.
Good at
- Audio‑video generation
- Text‑to‑video synthesis
- Image‑to‑video conversion
Limits
- No factual inference capability
- May amplify societal biases
- Requires large VRAM
Best for
- Local video generation
- Text‑driven video creation
- Audio‑visual content creation
Who it’s for. Developers and researchers who need a local, open‑weight audio‑video generation model. It is suitable for users with GPUs that can handle the memory requirements of the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 13.0 GB | 15.0 GB | Too big | Get file → | |
| Q6_K | 16.1 GB | 18.6 GB | Too big | Get file → | |
| Q8_0 | 20.6 GB | 23.6 GB | Too big | Get file → |
For a 8 GB VRAM budget, the Q4_K_M quantization (12.97 GB file, 15 GB estimated memory at 8 k context) is the smallest available but still exceeds 8 GB. If your GPU can provide 15 GB or more, Q4_K_M is recommended. For 18 GB VRAM, Q6_K (16.12 GB file, 18.6 GB memory) is suitable. For 23 GB VRAM, Q8_0 (20.61 GB file, 23.6 GB memory) offers the highest precision.
What GPU do you need for LTX 2.3 backup?
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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q4_K_M (13.0 GB file, about 15.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (20.6 GB file, about 23.6 GB in use).
Which LTX 2.3 backup quant should you choose?
Q4_K_M is the usual starting point for LTX 2.3 backup: it balances file size and quality well. Here it is a 13.0 GB file.
The Q8_0 file is 20.6 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LTX 2.3 backup
How much VRAM does LTX 2.3 backup need?
About 15.0 GB at Q4_K_M with an 8K context window. That is the 13.0 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 2.3 backup on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of LTX 2.3 backup GGUF?
It depends on the quant: Q4_K_M is 13.0 GB, Q6_K is 16.1 GB, Q8_0 is 20.6 GB.
Where can I download LTX 2.3 backup GGUF?
The files are on Hugging Face in the ExpertAtCoding/LTX-2.3-backup repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run LTX 2.3 backup on a GPU with 8 GB VRAM?
No. The smallest quantization requires 15 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does the model support local inference?
Yes. It can be run locally with llama.cpp and the provided GGUF files.
What license applies to this model?
The license is not specified in the provided information.