LTX 2.5 uncensored v1.1 FP8 needs about 8.9 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 6 quants, from 7.5 GB (Q4_K_M) to 22.3 GB (Q8_0).
LTX 2.5 uncensored v1.1 FP8 – a Gemma4 21B text‑to‑video model with baked‑in LoRAs
LTX 2.5 uncensored v1.1 FP8 is a 21B‑parameter Gemma4 model optimized for text‑to‑video generation. It includes five fine‑tuned LoRAs for NSFW, instruction following, and image‑to‑video control. The model is available in multiple GGUF quantizations for different memory budgets.
Good at
- Text‑to‑video with 4‑step generation
- Image‑to‑video control via IC‑LoRA
- Fast inference with FP8 scaling
Limits
- No vision support beyond video generation
- License unknown, use with caution
- Requires 8‑k context for memory estimates
Best for
- Creating short animated clips from text prompts
- Generating video from reference images
- Rapid prototyping of video content
Who it’s for. Developers and content creators who need a fast, fine‑tuned text‑to‑video model. The model is suitable for users with access to GPU hardware that can handle the memory requirements of the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 7.5 GB | 8.9 GB | Too big | Get file → | |
| Q6_K | 10.8 GB | 12.6 GB | Too big | Get file → | |
| Q8_0 | 14.0 GB | 16.1 GB | Too big | Get file → | |
| Q4_K_M | 14.2 GB | 16.4 GB | Too big | Get file → | |
| Q6_K | 17.8 GB | 20.4 GB | Too big | Get file → | |
| Q8_0 | 22.3 GB | 25.5 GB | Too big | Get file → |
For 8‑GB VRAM, use Q4_K_M (7.51 GB file, 8.9 GB memory at 8‑k context). For 12‑GB VRAM, Q6_K (10.81 GB file, 12.6 GB memory) is suitable. For larger GPUs, Q8_0 (13.97 GB file, 16.1 GB memory) offers higher precision.
What GPU do you need for LTX 2.5 uncensored v1.1 FP8?
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 (7.5 GB file, about 8.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (10.8 GB file, about 12.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (17.8 GB file, about 20.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (22.3 GB file, about 25.5 GB in use).
Which LTX 2.5 uncensored v1.1 FP8 quant should you choose?
Q4_K_M is the usual starting point for LTX 2.5 uncensored v1.1 FP8: it balances file size and quality well. Here it is a 7.5 GB file.
The Q8_0 file is 14.0 GB, about 1.9 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 2.5 uncensored v1.1 FP8
How much VRAM does LTX 2.5 uncensored v1.1 FP8 need?
About 8.9 GB at Q4_K_M with an 8K context window. That is the 7.5 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 uncensored v1.1 FP8 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of LTX 2.5 uncensored v1.1 FP8 GGUF?
It depends on the quant: Q4_K_M is 7.5 GB, Q6_K is 10.8 GB, Q8_0 is 14.0 GB, Q4_K_M is 14.2 GB, Q6_K is 17.8 GB, Q8_0 is 22.3 GB.
Where can I download LTX 2.5 uncensored v1.1 FP8 GGUF?
The files are on Hugging Face in the frtertaer/LTX-2.5-uncensored-v1.1-FP8 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 uncensored v1.1 FP8 use?
Hugging Face lists the license as unknown. 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 uncensored v1.1 FP8 on 8 GB VRAM?
Yes, the Q4_K_M quantization requires 8.9 GB memory at 8‑k context, which fits an 8‑GB VRAM setup with some headroom.
Does the model support image‑to‑video generation?
Yes, the baked‑in IC‑LoRA allows image‑to‑video control within the same model.
What is the context length supported by the model?
The model uses an 8‑k token context for memory estimates; larger contexts are not specified.