LT

LTX 2.3 uncensored v1.4 FP8

LtxGGUF by 0xSojalSecUpdated 2026-09-27
Download on Hugging Face
Parameters21B
Context128K
Layers48
Architecturegemma3
Smallest quant7.3 GB
Quick answer

LTX 2.3 uncensored v1.4 FP8 needs about 11.0 GB of memory at Q4_K_M (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 7 quants, from 7.3 GB (Q4_K_M) to 22.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

LTX 2.3 uncensored v1.4 FP8 – a DiT-based audio‑video foundation model

LTX 2.3 uncensored v1.4 FP8 is a gemma3 architecture model with 21 billion parameters. It supports text‑to‑video, image‑to‑video, and audio‑to‑video modes. The model is available in several GGUF quantizations for local inference.

Good at

  • Text‑to‑video generation
  • Image‑to‑video with identity preservation
  • Audio‑to‑video synthesis

Limits

  • No factual knowledge capability
  • Potential bias amplification
  • Inappropriate content generation risk

Best for

  • Creating short cinematic clips
  • Generating video from still images
  • Producing audio‑driven video content

Who it’s for. Developers and creators who need a local, open‑weight audio‑video generation model. The model is suitable for experimentation and production use where local inference is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M7.3 GB 11.0 GB
Too big Get file →
Q4_K_M14.2 GB 17.9 GB
Too big Get file →
Q4_K_M14.3 GB 18.0 GB
Too big Get file →
Q6_K17.8 GB 21.5 GB
Too big Get file →
Q6_K17.8 GB 21.5 GB
Too big Get file →
Q8_022.7 GB 26.5 GB
Too big Get file →
Q8_022.8 GB 26.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (7.3 GB file, 11 GB memory at 8k context). For 12 GB VRAM, Q6_K (17.76 GB file, 21.5 GB memory) is suitable. For 16 GB VRAM, Q8_0 (22.74 GB file, 26.5 GB memory) provides the highest quality.

What GPU do you need for LTX 2.3 uncensored v1.4 FP8?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 (7.3 GB file, about 11.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (7.3 GB file, about 11.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (17.8 GB file, about 21.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (22.8 GB file, about 26.5 GB in use).

Which LTX 2.3 uncensored v1.4 FP8 quant should you choose?

Q4_K_M is the usual starting point for LTX 2.3 uncensored v1.4 FP8: it balances file size and quality well. Here it is a 7.3 GB file.

The Q8_0 file is 22.7 GB, about 3.1 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

Architecturegemma3
Parameters21B
Layers48
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized by0xSojalSec
FamilyLtx
Licenseunknown
Downloads (HF)1,727
Last updated2026-09-27

Frequently asked questions about LTX 2.3 uncensored v1.4 FP8

How much VRAM does LTX 2.3 uncensored v1.4 FP8 need?

About 11.0 GB at Q4_K_M with an 8K context window. That is the 7.3 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 2.3 uncensored v1.4 FP8 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LTX 2.3 uncensored v1.4 FP8 GGUF?

It depends on the quant: Q4_K_M is 7.3 GB, Q4_K_M is 14.2 GB, Q4_K_M is 14.3 GB, Q6_K is 17.8 GB, Q6_K is 17.8 GB, Q8_0 is 22.7 GB and 1 more.

What context length does LTX 2.3 uncensored v1.4 FP8 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download LTX 2.3 uncensored v1.4 FP8 GGUF?

The files are on Hugging Face in the 0xSojalSec/LTX-2.3-uncensored-v1.4-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 2.3 uncensored v1.4 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 2.3 on 8 GB VRAM?

Yes, the Q4_K_M quantization (7.3 GB file) can run on 8 GB VRAM with an estimated 11 GB memory usage at 8k context.

Does the model support vision input?

No, the model does not provide vision support beyond image‑to‑video conversion via the built‑in nodes.

What license applies to this model?

The license is listed as unknown; use the model under the terms provided by the repository.

Other GGUFs of LTX-2.3

Similar models

Browse all →

More from 0xSojalSec

All by 0xSojalSec →

More Ltx models

All Ltx →

Other medium models

All medium models →