LT

LTX 2.5

LtxGGUF by vantagewithaiUpdated 2026-08-13
Download on Hugging Face
Parameters21B
Context—
Layers—
Architectureltxv
Smallest quant12.1 GB
Quick answer

LTX 2.5 needs about 18.1 GB of memory at Q4_K_M (a 15.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 26 quants, from 12.1 GB (Q2_K) to 23.6 GB (Q8_0).

LTX 2.5 – 21B parameter open‑world model for video, audio, and world simulation

LTX 2.5 is a 21 billion parameter transformer built for local execution and fine‑tuning. It generates synchronized, high‑fidelity video and audio from text, image, and video inputs. The model is available in multiple GGUF quantizations.

Good at

  • Video and audio generation from multimodal prompts
  • Fine‑tuning on local infrastructure
  • High‑fidelity synchronized output

Limits

  • No vision support in quantized form
  • Large memory requirement for higher‑quality quants
  • License requires paid agreement for commercial use over $10M revenue

Best for

  • Local video synthesis projects
  • Audio‑visual content creation
  • Fine‑tuning for custom media workflows

Who it’s for. Developers and content creators who need a local, fine‑tunable model for video and audio generation. The model supports self‑hosting on personal or enterprise infrastructure.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.1 GB 14.1 GB
Too big Get file →
Q2_K12.1 GB 14.1 GB
Too big Get file →
Q3_K_S12.6 GB 14.7 GB
Too big Get file →
Q3_K_S12.6 GB 14.7 GB
Too big Get file →
Q3_K_M12.9 GB 15.0 GB
Too big Get file →
Q3_K_M12.9 GB 15.0 GB
Too big Get file →
Q4_015.2 GB 17.6 GB
Too big Get file →
Q4_015.2 GB 17.6 GB
Too big Get file →
Q4_K_S15.3 GB 17.7 GB
Too big Get file →
Q4_K_S15.3 GB 17.7 GB
Too big Get file →
Q4_115.5 GB 17.9 GB
Too big Get file →
Q4_115.5 GB 17.9 GB
Too big Get file →
Q4_K_M15.7 GB 18.1 GB
Too big Get file →
Q4_K_M15.7 GB 18.1 GB
Too big Get file →
Q5_K_S15.9 GB 18.3 GB
Too big Get file →
Q5_K_S15.9 GB 18.3 GB
Too big Get file →
Q5_016.0 GB 18.4 GB
Too big Get file →
Q5_016.0 GB 18.4 GB
Too big Get file →
Q5_116.3 GB 18.7 GB
Too big Get file →
Q5_116.3 GB 18.7 GB
Too big Get file →
Q5_K_M18.1 GB 20.8 GB
Too big Get file →
Q5_K_M18.1 GB 20.8 GB
Too big Get file →
Q6_K18.6 GB 21.4 GB
Too big Get file →
Q6_K18.6 GB 21.4 GB
Too big Get file →
Q8_023.6 GB 26.9 GB
Too big Get file →
Q8_023.6 GB 26.9 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (12.13 GB file, ~14.1 GB memory). For 16 GB VRAM, Q4_0 (15.24 GB file, ~17.6 GB memory) or Q4_K_S. For 24 GB VRAM, Q5_K_M (18.12 GB file, ~20.8 GB memory) or Q6_K (18.62 GB file, ~21.4 GB memory).

What GPU do you need for LTX 2.5?

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: the best quant that fits is Q3_K_M (12.9 GB file, about 15.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (18.6 GB file, about 21.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (23.6 GB file, about 26.9 GB in use).

Which LTX 2.5 quant should you choose?

Q4_K_M is the usual starting point for LTX 2.5: it balances file size and quality well. Here it is a 15.7 GB file.

The Q8_0 file is 23.6 GB, about 1.5 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.

If memory is tight, the smallest file is Q2_K at 12.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureltxv
Parameters21B

Source

Quantized byvantagewithai
FamilyLtx
Licenseother
Downloads (HF)16,743
Last updated2026-08-13

Frequently asked questions about LTX 2.5

How much VRAM does LTX 2.5 need?

About 18.1 GB at Q4_K_M with an 8K context window. That is the 15.7 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LTX 2.5 GGUF?

It depends on the quant: Q2_K is 12.1 GB, Q2_K is 12.1 GB, Q3_K_S is 12.6 GB, Q3_K_S is 12.6 GB, Q3_K_M is 12.9 GB, Q3_K_M is 12.9 GB and 20 more.

Where can I download LTX 2.5 GGUF?

The files are on Hugging Face in the vantagewithai/LTX-2.5-GGUF 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 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 LTX 2.5 on 8 GB VRAM?

Use the Q2_K quant, which requires about 14.1 GB of VRAM at 8k context. It will not fit in 8 GB VRAM without swapping.

Is LTX 2.5 licensed for commercial use?

Under $10M annual revenue it is free under the LTX‑2.x Community License. Over $10M requires a paid commercial use agreement.

Does LTX 2.5 support vision tasks?

The quantized GGUF files do not include vision support; the model is focused on video and audio generation.

Other GGUFs of LTX-2.5

Similar models

Browse all →

More from vantagewithai

All by vantagewithai →

More Ltx models

All Ltx →

Other medium models

All medium models →