LTX 2.5 needs about 24.6 GB of memory at its main file (a 21.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 12.5 GB (Q4_0) to 22.8 GB (Q8_0).
LTX‑2.5 22B Distilled Transformer in GGUF format
LTX‑2.5 is a 21‑billion‑parameter distilled transformer model. The GGUF quantizations support text‑to‑video, image‑to‑video, and frame‑to‑video workflows in ComfyUI. The model is available in Q4_0, unknown, and Q8_0 quantizations.
Good at
- Text‑to‑video generation
- Image‑to‑video animation
- Frame interpolation
Limits
- No vision support in the transformer
- Large VRAM requirement for higher quantizations
- License type is other
Best for
- ComfyUI video generation pipelines
- Text‑driven animation projects
- Keyframe video interpolation
Who it’s for. Developers and artists using ComfyUI who need a transformer for video generation. The model works with the required CLIP, VAE, and audio VAE weights.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 12.5 GB | 14.5 GB | Too big | Get file → | |
| — | 21.5 GB | 24.6 GB | Too big | Get file → | |
| Q8_0 | 22.8 GB | 26.0 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_0 quantization (file size 12.51 GB, estimated 14.5 GB memory). If more VRAM is available, Q8_0 (22.78 GB, 26 GB memory) gives full precision. The unknown quant is larger and not recommended for limited memory.
What GPU do you need for LTX 2.5?
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_0 (12.5 GB file, about 14.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_0 (12.5 GB file, about 14.5 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 2.5 quant should you choose?
If memory is tight, the smallest file is Q4_0 at 12.5 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LTX 2.5
How much VRAM does LTX 2.5 need?
About 24.6 GB at its main file with an 8K context window. That is the 21.5 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 2.5 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of LTX 2.5 GGUF?
It depends on the quant: Q4_0 is 12.5 GB, file is 21.5 GB, Q8_0 is 22.8 GB.
Where can I download LTX 2.5 GGUF?
The files are on Hugging Face in the molbal/LTX-2.5-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 2.5 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‑2.5 on 8 GB VRAM?
Use the Q4_0 quantization; it requires about 14.5 GB of VRAM at 8k context, which is close to 8 GB but may need off‑load.
What additional weights are needed for ComfyUI?
Place Gemma 4 12B CLIP, ltx‑2.5‑video‑vae‑bf16.safetensors, and ltx‑2.5‑audio‑vae‑bf16.safetensors in the respective folders.
Is the model suitable for text‑to‑image tasks?
The model is a transformer for video generation; it does not provide vision capabilities for image tasks.