LT

Nz LTX25 weights

LtxGGUF by RootportUpdated 2026-10-16
Download on Hugging Face
Parameters21B
Context—
Layers—
Architectureltxv
Smallest quant14.7 GB
Quick answer

Nz LTX25 weights needs about 17.0 GB of memory at its main file (a 14.7 GB file) with an 8K context window, so it fits on a 24 GB GPU.

21‑billion‑parameter LTX 2.5 weight set for AviUtl2 plugin

Nz LTX25 weights provide the full model for the AviUtl2 plugin Nz‑Videomni. The GGUF file is 14.74 GB and requires about 17 GB of VRAM at 8 k context. It is derived from Lightricks LTX‑2.5 and is not a new training.

Good at

  • Video generation on AviUtl2
  • LTX‑2.5 compatible workflows
  • Large‑context inference

Limits

  • Requires 17 GB VRAM at 8 k context
  • No vision support
  • License is other

Best for

  • AviUtl2 video editing
  • LTX‑2.5 plugin integration
  • High‑resolution video generation

Who it’s for. Users of the Nz‑Videomni plugin who need the full LTX‑2.5 weight set. The model is not compatible with LTX‑2.3 weights and must be placed in the models/LTX25 folder.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—14.7 GB 17.0 GB
Too big Get file →

The only available GGUF file is 14.74 GB with unknown quant. It needs about 17 GB of VRAM at 8 k context. For lower memory budgets, a different quantization would be required, but none is provided here.

What GPU do you need for Nz LTX25 weights?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is the main file (14.7 GB file, about 17.0 GB in use).

Specifications

Architecture from the GGUF header

Architectureltxv
Parameters21B

Source

Quantized byRootport
FamilyLtx
Licenseother
Downloads (HF)1,453
Last updated2026-10-16

Frequently asked questions about Nz LTX25 weights

How much VRAM does Nz LTX25 weights need?

About 17.0 GB at its main file with an 8K context window. That is the 14.7 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 Nz LTX25 weights on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nz LTX25 weights GGUF?

It depends on the quant: file is 14.7 GB.

Where can I download Nz LTX25 weights GGUF?

The files are on Hugging Face in the Rootport/Nz-LTX25-weights repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Nz LTX25 weights 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 this model on 8 GB VRAM?

No. The model requires about 17 GB of VRAM at 8 k context.

What license does this model use?

The license is listed as other.

How do I install the weights?

Copy the repository structure into the models/LTX25 folder of Nz‑Videomni.

Other GGUFs of LTX-2.5

Similar models

Browse all →

More from Rootport

All by Rootport →

More Ltx models

All Ltx →

Other medium models

All medium models →