LT

LTX 2.3

LtxGGUF by MakiAiUpdated 2026-04-02
Download on Hugging Face
Parameters21B
Context—
Layers—
Architectureltxv
Smallest quant8.3 GB
Quick answer

LTX 2.3 needs about 16.5 GB of memory at Q4_K_M (a 14.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 44 quants, from 8.3 GB (Q2_K) to 42.0 GB (F16).

LTX 2.3 – 21B parameter audio‑video diffusion model

LTX 2.3 is a 21B parameter diffusion model for synchronized audio and video generation. It is built on the ltxv architecture and supports English prompts. The model is available in multiple GGUF quantizations for local inference.

Good at

  • Synchronized audio‑video generation
  • High‑quality visual output
  • Fast inference with distilled variants

Limits

  • No factual knowledge support
  • May produce biased or inappropriate content
  • Requires 8‑k context for memory estimates

Best for

  • Local video creation workflows
  • Rapid prototyping with distilled models
  • ComfyUI integration for batch generation

Who it’s for. Developers and creators who need a local, open‑weight audio‑video generation model. The model is suitable for users with access to a GPU and the ability to run llama.cpp or ComfyUI pipelines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K8.3 GB 9.8 GB
Too big Get file →
Q2_K8.3 GB 9.8 GB
Too big Get file →
Q2_K9.0 GB 10.6 GB
Too big Get file →
Q2_K9.0 GB 10.6 GB
Too big Get file →
Q3_K_S9.9 GB 11.6 GB
Too big Get file →
Q3_K_S9.9 GB 11.6 GB
Too big Get file →
Q3_K_S10.5 GB 12.2 GB
Too big Get file →
Q3_K_S10.5 GB 12.2 GB
Too big Get file →
Q3_K_M10.8 GB 12.6 GB
Too big Get file →
Q3_K_M10.8 GB 12.6 GB
Too big Get file →
Q3_K_M11.8 GB 13.7 GB
Too big Get file →
Q3_K_M11.8 GB 13.8 GB
Too big Get file →
Q4_012.7 GB 14.7 GB
Too big Get file →
Q4_012.7 GB 14.7 GB
Too big Get file →
Q4_K_S13.1 GB 15.2 GB
Too big Get file →
Q4_K_S13.1 GB 15.2 GB
Too big Get file →
Q4_K_S13.7 GB 15.9 GB
Too big Get file →
Q4_K_S13.7 GB 15.9 GB
Too big Get file →
Q4_113.8 GB 15.9 GB
Too big Get file →
Q4_113.8 GB 15.9 GB
Too big Get file →
Q4_K_M14.3 GB 16.5 GB
Too big Get file →
Q4_K_M14.3 GB 16.5 GB
Too big Get file →
Q4_K_M15.1 GB 17.4 GB
Too big Get file →
Q4_K_M15.1 GB 17.4 GB
Too big Get file →
Q5_K_S15.2 GB 17.6 GB
Too big Get file →
Q5_K_S15.2 GB 17.6 GB
Too big Get file →
Q5_015.3 GB 17.6 GB
Too big Get file →
Q5_015.3 GB 17.6 GB
Too big Get file →
Q5_K_S15.8 GB 18.2 GB
Too big Get file →
Q5_K_S15.8 GB 18.2 GB
Too big Get file →
Q5_K_M16.1 GB 18.5 GB
Too big Get file →
Q5_K_M16.1 GB 18.5 GB
Too big Get file →
Q5_116.3 GB 18.8 GB
Too big Get file →
Q5_116.3 GB 18.8 GB
Too big Get file →
Q5_K_M17.1 GB 19.6 GB
Too big Get file →
Q5_K_M17.1 GB 19.6 GB
Too big Get file →
Q6_K17.8 GB 20.4 GB
Too big Get file →
Q6_K17.8 GB 20.4 GB
Too big Get file →
Q8_022.8 GB 26.0 GB
Too big Get file →
Q8_022.8 GB 26.0 GB
Too big Get file →
BF1642.0 GB 47.6 GB
Too big Get file →
F1642.0 GB 47.6 GB
Too big Get file →
BF1642.0 GB 47.6 GB
Too big Get file →
F1642.0 GB 47.6 GB
Too big Get file →

For 8‑GB VRAM, use Q2_K (8.28 GB) or Q3_K_S (9.95 GB). For 12‑GB VRAM, Q4_0 (12.72 GB) or Q4_K_S (13.12 GB) are suitable. For 16‑GB VRAM, Q4_K_M (14.33 GB) or Q5_K_S (15.25 GB) provide a balance of size and quality. Memory estimates are approximate.

What GPU do you need for LTX 2.3?

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 Q3_K_S (9.9 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (13.8 GB file, about 15.9 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 (22.8 GB file, about 26.0 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (42.0 GB file, about 47.6 GB in use).

Which LTX 2.3 quant should you choose?

Q4_K_M is the usual starting point for LTX 2.3: it balances file size and quality well. Here it is a 14.3 GB file.

The Q8_0 file is 22.8 GB, about 1.6 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 8.3 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 byMakiAi
FamilyLtx
Licenseother
Downloads (HF)782
Last updated2026-04-02

Frequently asked questions about LTX 2.3

How much VRAM does LTX 2.3 need?

About 16.5 GB at Q4_K_M with an 8K context window. That is the 14.3 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LTX 2.3 GGUF?

It depends on the quant: Q2_K is 8.3 GB, Q2_K is 8.3 GB, Q2_K is 9.0 GB, Q2_K is 9.0 GB, Q3_K_S is 9.9 GB, Q3_K_S is 9.9 GB and 38 more.

Where can I download LTX 2.3 GGUF?

The files are on Hugging Face in the MakiAi/LTX-2.3-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 2.3 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 2.3 on 8 GB VRAM?

Yes, using Q2_K or Q3_K_S quantizations will fit within 8 GB VRAM, though memory estimates are approximate.

Does LTX 2.3 support text prompts in languages other than English?

The model is trained for English; other languages are not supported.

Is LTX 2.3 suitable for generating speech audio?

The model can generate audio, but speech quality may be lower compared to dedicated speech models.

Other GGUFs of LTX-2.3

Similar models

Browse all →

More from MakiAi

All by MakiAi →

More Ltx models

All Ltx →

Other medium models

All medium models →