LT

LTX 2.5 22B dev uncensored ROCmFPX

LtxGGUF by Harsha001Updated 2026-10-22
Download on Hugging Face
Parameters13.1B
Context—
Layers—
Architecture—
Smallest quant14.7 GB
Quick answer

LTX 2.5 22B dev uncensored ROCmFPX needs about 16.9 GB of memory at Q8_0 (a 14.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 14.7 GB (Q8_0) to 14.7 GB (Q4_0).

LTX 2.5 22B dev uncensored ROCmFPX – 13.1B parameter LTX model

LTX 2.5 22B dev uncensored ROCmFPX is a 13.1B parameter language model derived from Lightricks LTX-2.5. It is optimized for ROCmFPX execution and offers uncensored text generation capabilities.

Good at

  • 13.1B parameters
  • Uncensored content
  • ROCmFPX optimization

Limits

  • No vision support
  • License type is other
  • Large memory requirement

Best for

  • Research on large language models
  • Fine-tuning with ROCm
  • Text generation tasks

Who it’s for. Developers and researchers who need a large LTX model with uncensored behavior and ROCmFPX support for advanced language tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_014.7 GB 16.9 GB
Too big Get file →
Q4_014.7 GB 17.0 GB
Too big Get file →

For 8‑GB VRAM, Q4_0 is the smallest file at 14.74 GB but still requires about 17 GB of memory at 8k context. Q8_0 is larger at 14.67 GB and needs about 16.9 GB of memory. Both estimates are approximate.

What GPU do you need for LTX 2.5 22B dev uncensored ROCmFPX?

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 Q4_0 (14.7 GB file, about 17.0 GB in use).

Which LTX 2.5 22B dev uncensored ROCmFPX quant should you choose?

Q8_0 (14.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters13.1B

Source

Quantized byHarsha001
FamilyLtx
Licenseother
Downloads (HF)2,182
Last updated2026-10-22

Frequently asked questions about LTX 2.5 22B dev uncensored ROCmFPX

How much VRAM does LTX 2.5 22B dev uncensored ROCmFPX need?

About 16.9 GB at Q8_0 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 LTX 2.5 22B dev uncensored ROCmFPX on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LTX 2.5 22B dev uncensored ROCmFPX GGUF?

It depends on the quant: Q8_0 is 14.7 GB, Q4_0 is 14.7 GB.

Where can I download LTX 2.5 22B dev uncensored ROCmFPX GGUF?

The files are on Hugging Face in the Harsha001/LTX-2.5-22B-dev-uncensored-ROCmFPX 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 22B dev uncensored ROCmFPX 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 16.9–17 GB of memory at 8k context, exceeding 8 GB VRAM.

What quantization options are available?

The model is available in Q8_0 and Q4_0 quantizations.

Is this model vision capable?

No, it does not support vision tasks.

Other GGUFs of LTX-2.5

Similar models

Browse all →

More from Harsha001

All by Harsha001 →

More Ltx models

All Ltx →

Other medium models

All medium models →