Nz Gemma4 12B LTX25 needs about 10.8 GB of memory at Q4_K_M (a 9.2 GB file) with an 8K context window, so it fits on a 12 GB GPU.
Gemma 4 12B LTX25 text encoder for AviUtl2 video plugin
Nz Gemma4 12B LTX25 is a GGUF quantized text encoder derived from Lightricks LTX‑2.5 fine‑tuned Gemma 4. It is intended for use with the Nz‑Videomni AviUtl2 plugin and is not compatible with general Gemma 4 chat applications.
Good at
- Fine‑tuned LTX‑2.5 text encoding
- Video generation plugin integration
- Low‑precision Q4_K_M quantization
Limits
- Only works with LTX‑2.5 plugin
- No general chat or vision support
- Requires separate VAE and upscaler
Best for
- AviUtl2 video editing workflows
- LTX‑2.5 text‑to‑video pipelines
- Custom video generation setups
Who it’s for. Developers and users of the Nz‑Videomni AviUtl2 plugin who need a lightweight text encoder for LTX‑2.5 video generation. It is not suitable for general-purpose language modeling.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 9.2 GB | 10.8 GB | Too big | Get file → |
The Q4_K_M quantization file is 9.23 GB and needs about 10.8 GB of VRAM at 8 k context. For 8 GB VRAM use, the model cannot run. For 12 GB VRAM use, it is feasible with some swapping. No other quants are provided.
What GPU do you need for Nz Gemma4 12B LTX25?
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 Q4_K_M (9.2 GB file, about 10.8 GB in use).
Which Nz Gemma4 12B LTX25 quant should you choose?
Q4_K_M is the usual starting point for Nz Gemma4 12B LTX25: it balances file size and quality well. Here it is a 9.2 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Nz Gemma4 12B LTX25
How much VRAM does Nz Gemma4 12B LTX25 need?
About 10.8 GB at Q4_K_M with an 8K context window. That is the 9.2 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 Nz Gemma4 12B LTX25 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Nz Gemma4 12B LTX25 GGUF?
It depends on the quant: Q4_K_M is 9.2 GB.
Where can I download Nz Gemma4 12B LTX25 GGUF?
The files are on Hugging Face in the Rootport/Nz-Gemma4-12B-LTX25 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 Gemma4 12B LTX25 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 Q4_K_M quant requires roughly 10.8 GB VRAM at 8 k context, exceeding 8 GB.
Is this model compatible with other Gemma 4 versions?
No, it is fine‑tuned for LTX‑2.5 and is not compatible with general Gemma 4 chat models.
Do I need additional files to run it?
Yes, the VAE, upscaler, and main video generation weights must be placed in the same LTX‑25 folder.