LTX 2.3 DEV needs about 16.4 GB of memory at Q4_K_M (a 14.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 10.6 GB (Q3_K_M) to 22.8 GB (Q8_0).
LTX 2.3 DEV – 21B parameter audio‑video diffusion model
LTX 2.3 DEV is a 21 billion parameter diffusion‑based audio‑video foundation model. It generates synchronized video and audio from text prompts. The model is available in multiple GGUF quantizations for local inference.
Good at
- Synchronized audio‑video generation
- Text‑to‑video synthesis
- Local inference with GGUF
Limits
- No factual knowledge or vision support
- Requires large VRAM for higher quantizations
- License is other, not open source
Best for
- Creating short video clips with audio
- Prototyping audio‑video generation workflows
- Testing diffusion models locally
Who it’s for. Developers and researchers who need a local, open‑weight audio‑video model for experimentation. The model is suitable for those who can manage the memory requirements and comply with the license terms.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 10.6 GB | 12.4 GB | Too big | Get file → | |
| Q4_K_S | 13.0 GB | 15.0 GB | Too big | Get file → | |
| Q4_K_M | 14.2 GB | 16.4 GB | Too big | Get file → | |
| Q5_K_M | 15.9 GB | 18.3 GB | Too big | Get file → | |
| Q8_0 | 22.8 GB | 26.0 GB | Too big | Get file → |
For 8 GB VRAM use Q3_K_M (10.63 GB file, 12.4 GB memory at 8k context). For 12 GB VRAM use Q4_K_S (12.96 GB file, 15 GB memory). For 16 GB VRAM use Q4_K_M (14.19 GB file, 16.4 GB memory). Higher quantizations need more memory.
What GPU do you need for LTX 2.3 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: 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_S (13.0 GB file, about 15.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (15.9 GB file, about 18.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (22.8 GB file, about 26.0 GB in use).
Which LTX 2.3 DEV quant should you choose?
Q4_K_M is the usual starting point for LTX 2.3 DEV: it balances file size and quality well. Here it is a 14.2 GB file.
The Q8_0 file is 22.8 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_M at 10.6 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 2.3 DEV
How much VRAM does LTX 2.3 DEV need?
About 16.4 GB at Q4_K_M with an 8K context window. That is the 14.2 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 DEV on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of LTX 2.3 DEV GGUF?
It depends on the quant: Q3_K_M is 10.6 GB, Q4_K_S is 13.0 GB, Q4_K_M is 14.2 GB, Q5_K_M is 15.9 GB, Q8_0 is 22.8 GB.
Where can I download LTX 2.3 DEV GGUF?
The files are on Hugging Face in the Viper-AI-Vaunt/LTX-2.3-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 2.3 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 2.3 DEV on 8 GB VRAM?
Use the Q3_K_M quantization; it requires about 12.4 GB memory at 8k context, which is close to 8 GB VRAM but may need swapping.
Does the model support text prompts in languages other than English?
The model is trained for English; other languages are not supported.
Is the model suitable for generating factual content?
No, the model is not intended to provide factual information and may amplify biases.