LT

LTXV2 comfy

LtxvGGUF by KijaiUpdated 2026-02-22
Download on Hugging Face
Parameters18.9B
Context—
Layers—
Architectureltxv
Smallest quant12.7 GB
Quick answer

LTXV2 comfy needs about 14.7 GB of memory at Q4_K_M (a 12.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 5 quants, from 12.7 GB (Q4_K_M) to 20.4 GB (Q8_0).

18.9B parameter LTXV2 comfy model for text and diffusion tasks

LTXV2 comfy is an 18.9B parameter model built on the ltxv architecture. It is available in several GGUF quantizations and is designed for use with ComfyUI and KJNodes. The model supports text and diffusion workflows with updated VAE handling.

Good at

  • Text generation
  • Diffusion model integration
  • ComfyUI compatibility

Limits

  • No vision support
  • Requires updated KJNodes or ComfyUI core
  • Large memory footprint

Best for

  • Fine‑tuning diffusion pipelines
  • Generating prompts for image models
  • Embedding‑based text tasks

Who it’s for. Users who work with ComfyUI and need a large language model that can be paired with diffusion models. It is suitable for developers building custom pipelines and researchers experimenting with text‑to‑image workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M12.7 GB 14.7 GB
Too big Get file →
Q4_K_M12.7 GB 14.7 GB
Too big Get file →
Q6_K15.9 GB 18.3 GB
Too big Get file →
Q8_020.4 GB 23.4 GB
Too big Get file →
Q8_020.4 GB 23.4 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (12.65 GB file, ~14.7 GB memory at 8k context). For 12 GB VRAM, Q6_K (15.92 GB file, ~18.3 GB memory). For 16 GB VRAM, Q8_0 (20.41 GB file, ~23.4 GB memory). Estimates are approximate.

What GPU do you need for LTXV2 comfy?

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 Q4_K_M (12.7 GB file, about 14.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (20.4 GB file, about 23.4 GB in use).

Which LTXV2 comfy quant should you choose?

Q4_K_M is the usual starting point for LTXV2 comfy: it balances file size and quality well. Here it is a 12.7 GB file.

The Q8_0 file is 20.4 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureltxv
Parameters18.9B

Source

Quantized byKijai
FamilyLtxv
Licenseother
Downloads (HF)23,615
Last updated2026-02-22

Frequently asked questions about LTXV2 comfy

How much VRAM does LTXV2 comfy need?

About 14.7 GB at Q4_K_M with an 8K context window. That is the 12.7 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 LTXV2 comfy on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LTXV2 comfy GGUF?

It depends on the quant: Q4_K_M is 12.7 GB, Q4_K_M is 12.7 GB, Q6_K is 15.9 GB, Q8_0 is 20.4 GB, Q8_0 is 20.4 GB.

Where can I download LTXV2 comfy GGUF?

The files are on Hugging Face in the Kijai/LTXV2_comfy repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does LTXV2 comfy 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 LTXV2 comfy on 8 GB VRAM?

Yes, with the Q4_K_M quantization the file is 12.65 GB and requires about 14.7 GB of VRAM at 8k context. It may need swapping or lower context.

Does LTXV2 comfy support vision tasks?

No, the model does not include vision capabilities. It is intended for text and diffusion workflows only.

What updates are needed for ComfyUI to load this model?

Use the latest KJNodes or a recent ComfyUI core that includes the updated VAE loader and embedding connector changes.

Similar models

Browse all →

More from Kijai

All by Kijai →

More Ltxv models

All Ltxv →

Other medium models

All medium models →