LT

LTX2.5 base

LtxGGUF by EllaPriest45Updated 2026-10-08
Download on Hugging Face
Parameters21B
Context—
Layers—
Architectureltxv
Smallest quant9.5 GB
Quick answer

LTX2.5 base needs about 17.4 GB of memory at Q4_K_M (a 15.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 9.5 GB (Q5_K_M) to 15.1 GB (Q4_K_M).

LTX2.5 base – 21B parameter LTX model

LTX2.5 base is a 21B parameter language model built on the ltxv architecture. It is available in GGUF format with two quantization options. The model has no explicit language or vision capabilities listed.

Good at

  • General text generation
  • Large context handling
  • Low‑latency inference

Limits

  • No license information provided
  • No language support listed
  • No vision capability

Best for

  • Small‑to‑medium projects requiring 21B parameters
  • Research prototypes
  • Custom fine‑tuning

Who it’s for. Developers and researchers who need a large LTX model for text‑only tasks and can manage the memory requirements. The model is suitable for environments where license constraints are not a concern.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M9.5 GB 11.2 GB
Too big Get file →
Q4_K_M15.1 GB 17.4 GB
Too big Get file →

For 8‑12 GB VRAM, use Q5_K_M (file size 9.51 GB, estimated 11.2 GB memory at 8k context). For 16 GB VRAM or higher, Q4_K_M (file size 15.09 GB, estimated 17.4 GB memory) is an option if you need higher precision.

What GPU do you need for LTX2.5 base?

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 Q5_K_M (9.5 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (9.5 GB file, about 11.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (15.1 GB file, about 17.4 GB in use).

Which LTX2.5 base quant should you choose?

Q4_K_M is the usual starting point for LTX2.5 base: it balances file size and quality well. Here it is a 15.1 GB file.

If memory is tight, the smallest file is Q5_K_M at 9.5 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureltxv
Parameters21B

Source

Quantized byEllaPriest45
FamilyLtx
Downloads (HF)1,211
Last updated2026-10-08

Frequently asked questions about LTX2.5 base

How much VRAM does LTX2.5 base need?

About 17.4 GB at Q4_K_M with an 8K context window. That is the 15.1 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 LTX2.5 base on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LTX2.5 base GGUF?

It depends on the quant: Q5_K_M is 9.5 GB, Q4_K_M is 15.1 GB.

Where can I download LTX2.5 base GGUF?

The files are on Hugging Face in the EllaPriest45/LTX2.5_base repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run LTX2.5 on 8 GB VRAM?

The Q5_K_M quant requires about 11.2 GB memory at 8k context, so 8 GB VRAM is insufficient.

Which quant should I use for 12 GB VRAM?

Q5_K_M is the best fit, as it uses 11.2 GB memory at 8k context.

Does this model support vision?

No, the model has no vision capabilities listed.

Similar models

Browse all →

More from EllaPriest45

All by EllaPriest45 →

More Ltx models

All Ltx →

Other medium models

All medium models →