What GPU do I need to run Lightricks/LTX-2?
A 18.9B-parameter video generation model. 18.9B parameters, published in BF16. View on Hugging Face
LTX-2 is published by Lightricks on Hugging Face, with 378,477 downloads and 1,776 likes to date. It's a unlisted-architecture model built for image-to-video, published natively in BF16.
What LTX-2 is
LTX-2 is a 18.9B-parameter video generation model published by Lightricks on Hugging Face, released under Custom license.
License note: a lab-specific license (tagged "other" on Hugging Face); read the model card's own license section before commercial use. Facts in this section are sourced from LTX-2's Hugging Face model card, not benchmarked by Aquanode.
What it's used for
- Text-to-video / image-to-video generation
- Short-form creative video
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for activation memory and allocator fragmentation. Diffusion and video models carry no KV-cache. The real driver of extra memory is output resolution and frame count, which this flat overhead does not model. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 35.2 GB | 42.2 GB | RTX A6000 | 1 | $0.363/hr |
| cheaper alt. | RTX 5060 Ti | 3 | $0.330/hr | ||
| FP8 (quantized) | 17.6 GB | 21.1 GB | RTX 4080 Super | 1 | $0.338/hr |
| cheaper alt. | RTX 5060 Ti | 2 | $0.220/hr | ||
| INT4 (quantized) | 8.8 GB | 10.5 GB | RTX 5060 Ti | 1 | $0.110/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run LTX-2 at its published (BF16) precision: 1× RTX A6000, at $0.363/hr per GPU ($0.363/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
LTX-2: common questions
Can LTX-2 run on a single GPU?
Yes, but not on a desktop card. At BF16 it needs 42.2 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest live single-card fit is a 48.0 GB RTX A6000 at $0.363/hr.
What is the least VRAM LTX-2 can run in?
10.5 GB, at INT4 (quantized), which fits a 12 GB card, against 42.2 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Does quantizing LTX-2 lower the GPU bill?
Yes. At BF16 the cheapest live fit is one RTX A6000 at $0.363/hr. At INT4 (quantized) it drops to one RTX 5060 Ti at $0.110/hr, provided a quantized checkpoint exists for it.
How to run LTX-2
Run LTX-2 with Diffusers (Python)
Generic example using Hugging Face's diffusers library, not from the model's own docs.
from diffusers import DiffusionPipeline
from diffusers.utils import export_to_video
import torch
pipe = DiffusionPipeline.from_pretrained("Lightricks/LTX-2", torch_dtype=torch.bfloat16)
pipe.to("cuda")
frames = pipe("a description of the scene").frames[0]
export_to_video(frames, "output.mp4", fps=24)Run LTX-2 with ComfyUI
Aquanode's ComfyUI template comes with ComfyUI preinstalled. Download Lightricks/LTX-2's checkpoint into the models folder and load it in a workflow; this is a real Aquanode template, but loading this specific checkpoint is a manual step, not a one-click deploy.
Deploy LTX-2 on Aquanode
Aquanode has no one-click deploy template for LTX-2; it comes with ComfyUI preinstalled, so you only need to load the checkpoint, not install anything. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch the ComfyUI template sized to the requirement above (1× RTX A6000 or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch the ComfyUI templateWeight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More LTX models
- LTX-2.5-Diffusers (19.0B, BF16)
- LTX-2.3-Diffusers (19.0B, BF16)
- LTX-Video (1.9B, F32)
- LTX-Video-0.9.5 (1.9B, BF16)
Related reading: RTX A6000 pricing and specs, The NVIDIA Inception program, explained, Google Colab alternatives for dedicated GPU access, Free GPU credits for students and researchers, and RunPod volume disk vs. network volume, compared.
