LTX 2.5 Comfy needs about 14.2 GB of memory at BF16 (a 12.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 6 quants, from 7.3 GB (BF16) to 22.7 GB (BF16).
LTX 2.5 Comfy – 22B parameter model for synchronized video and audio generation
LTX 2.5 Comfy is a 22‑billion‑parameter model built for local execution and fine‑tuning. It generates synchronized video and audio in a single pass from text, image, and video inputs. The GGUF quantizations reduce the 39‑GB BF16 transformer to 11‑23 GB for consumer hardware.
Good at
- Synchronized video and audio generation
- Native multishot scene continuity
- Efficient diffusion rendering
Limits
- Requires 8‑k context for memory estimates
- No vision support specified
- License type is other
Best for
- Local video synthesis
- Audio‑video sync projects
- Fine‑tuning on custom datasets
Who it’s for. Developers and researchers needing a local, open‑weight model for high‑fidelity video and audio generation. The model is suitable for users with GPUs capable of handling 8‑k context and the specified VRAM ranges.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 7.3 GB | 8.7 GB | Too big | Get file → | |
| BF16 | 9.4 GB | 11.1 GB | Too big | Get file → | |
| BF16 | 12.2 GB | 14.2 GB | Too big | Get file → | |
| BF16 | 14.8 GB | 17.1 GB | Too big | Get file → | |
| BF16 | 17.6 GB | 20.2 GB | Too big | Get file → | |
| BF16 | 22.7 GB | 25.9 GB | Too big | Get file → |
For 16 GB VRAM, use the BF16 quantization at 11.1 GB (est. 8‑k context 11.1 GB). For 24 GB VRAM, the 14.83 GB variant is suitable. For larger GPUs, the 22.66 GB variant offers higher fidelity. Memory estimates are approximate.
What GPU do you need for LTX 2.5 Comfy?
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: the best quant that fits is BF16 (9.4 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (12.2 GB file, about 14.2 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (17.6 GB file, about 20.2 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (22.7 GB file, about 25.9 GB in use).
Which LTX 2.5 Comfy quant should you choose?
BF16 (12.2 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is BF16 at 7.3 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LTX 2.5 Comfy
How much VRAM does LTX 2.5 Comfy need?
About 14.2 GB at BF16 with an 8K context window. That is the 12.2 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 2.5 Comfy on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of LTX 2.5 Comfy GGUF?
It depends on the quant: BF16 is 7.3 GB, BF16 is 9.4 GB, BF16 is 12.2 GB, BF16 is 14.8 GB, BF16 is 17.6 GB, BF16 is 22.7 GB.
Where can I download LTX 2.5 Comfy GGUF?
The files are on Hugging Face in the agosh/LTX-2.5-Comfy-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 Comfy 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 Comfy on a 16 GB RTX 4080?
Yes, the BF16 11.1 GB quantization fits within 16 GB VRAM, leaving room for execution context.
Does the model support vision inputs?
Vision support is not specified in the provided facts.
What is the VRAM requirement for the 22.66 GB quantization?
The 22.66 GB quantization requires approximately 25.9 GB VRAM at 8‑k context.