LTX 2 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 – 19B diffusion audio‑video model for local generation
LTX 2 is a 19‑billion‑parameter diffusion model that generates synchronized video and audio. It is built on the ltxv architecture and supports text‑to‑video and image‑to‑video pipelines. The model is available in multiple GGUF quantizations for local inference.
Good at
- Text‑to‑video generation
- Image‑to‑video conversion
- Audio‑video synchronization
Limits
- No vision support in the base model
- Requires 8‑k context for memory estimates
- License terms not specified
Best for
- Creating short video clips from text prompts
- Generating video from still images
- Local inference on GPUs with 8‑k context
Who it’s for. Developers and researchers who need a local, diffusion‑based audio‑video model. It is suitable for users with access to a GPU and the ability to run llama.cpp or compatible inference engines.
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 8‑GB VRAM, use Q4_K_M (file size 12.97 GB, estimated 15 GB memory). For 12‑GB VRAM, Q6_K (16.12 GB, 18.6 GB memory). For 16‑GB VRAM or higher, Q8_0 (20.61 GB, 23.6 GB memory). Estimates are approximate.
What GPU do you need for LTX 2?
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 quant should you choose?
Q4_K_M is the usual starting point for LTX 2: 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
How much VRAM does LTX 2 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 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 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 GGUF?
The files are on Hugging Face in the DeepBeepMeep/LTX-2 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 on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires about 15 GB of VRAM at 8‑k context. The file size is 12.97 GB.
Does LTX 2 support image‑to‑video generation?
Yes, the model includes image‑to‑video pipelines as part of its diffusion architecture.
What context length does LTX 2 need?
The memory estimates are based on an 8‑k context length; larger contexts will increase VRAM usage.