LT

LTX 2.5 uncensored v1.1 FP8

LtxGGUF by ChrisColeTechUpdated 2026-10-15
Download on Hugging Face
Parameters21B
Context—
Layers—
Architecturegemma4
Smallest quant7.5 GB
Quick answer

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 21‑billion‑parameter Gemma4 model optimized for text‑to‑video generation. It includes five fine‑tuned LoRAs for NSFW, instruction following, reference adherence, detail enhancement, and image‑to‑video control. The model is distributed as GGUF files in FP8 for speed.

Good at

  • Fast text‑to‑video with 4‑step generation
  • High‑quality NSFW content via Eros10 LoRA
  • Strong instruction following with DMD Distilled LoRA

Limits

  • No vision support – only text‑to‑video
  • License unknown, use with caution
  • Requires 8‑k context for memory estimates

Best for

  • Creating short video clips from text prompts
  • Generating NSFW video content with high coherence
  • Fine‑tuning video generation for specific styles

Who it’s for. Developers and researchers needing a fast, FP8‑optimized text‑to‑video model with multiple baked‑in LoRAs. Suitable for local deployment on systems with sufficient VRAM and RAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M7.5 GB 8.9 GB
Too big Get file →
Q6_K10.8 GB 12.6 GB
Too big Get file →
Q8_014.0 GB 16.1 GB
Too big Get file →
Q4_K_M14.2 GB 16.4 GB
Too big Get file →
Q6_K17.8 GB 20.4 GB
Too big Get file →
Q8_022.3 GB 25.5 GB
Too big Get file →

For 8‑GB VRAM, use Q4_K_M (7.51 GB, ~8.9 GB memory at 8k context). For 12‑GB VRAM, Q6_K (10.81 GB, ~12.6 GB memory). For 16‑GB VRAM, Q8_0 (13.97 GB, ~16.1 GB memory). Larger models require more VRAM and RAM.

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

Architecturegemma4
Parameters21B

Source

Quantized byChrisColeTech
FamilyLtx
Licenseunknown
Downloads (HF)82,063
Last updated2026-10-15

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 ChrisColeTech/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, using the Q4_K_M quantized file (7.51 GB) will fit within 8 GB VRAM, with an estimated memory usage of about 8.9 GB at 8k context.

Does this model support image or audio input?

No, the model is text‑to‑video only and does not accept image or audio inputs.

What are the LoRA strengths in this build?

The baked‑in LoRAs have strengths of 0.7 for Eros10 and LTX Video IC‑LoRA, 1.0 for DMD Distilled, and 0.45 for LTX Video IC‑LoRA Detailer and Img2Vid LoRA.

Other GGUFs of LTX-2.5

Similar models

Browse all →

More from ChrisColeTech

All by ChrisColeTech →

More Ltx models

All Ltx →

Other medium models

All medium models →