LTX-Video by LTX.io: Open-Weight Model

Runs On

What it takes to serve LTX-Video (1.9B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

Precision	Weights	Memory needed	Cheapest setup	Per hour	Also fits
16-bit	3.8 GB	4.6 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
8-bit	1.9 GB	2.3 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
4-bit	1.0 GB	1.2 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

SAVRN's Notes on LTX-Video

Four and a half gigabytes is the whole hardware story for LTX-Video. The 1.9B-parameter image-to-video model carries 3.8 GB of 16-bit weights and needs 4.6 GB of memory, dropping to 2.3 GB at 8-bit and 1.2 GB at 4-bit. On the cheapest setup the SAVRN Index prices, one 192 GB MI300X at $1.85 an hour, that is under three percent of the card. Nobody sizes a rack around this; the decision is what else shares the GPU.

The license is listed as other, and the publisher's card names a separate license for each 2B version from 0.9 through 0.9.6-dev, so the terms depend on the checkpoint you pull. The repository holds 63 files and 254 GB while the model you serve is under 4 GB: pick the version, read its license, fetch only that one. No Index host prices it, so the card hour is your cost reference.

SAVRN Research, 2026-09-18

Model Card

This model card focuses on the model associated with the LTX-Video model, codebase available here. LTX-Video is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 30 FPS videos at a 1216×704 resolution faster than they can be watched. Trained on a large-scale dataset of diverse videos, the model generates high-resolution videos with realistic and varied content. You can use the model for purposes under the license: - 2B version 0.9: license - 2B version 0.9.1 license - 2B version 0.9.5 license - 2B version 0.9.6-dev license - 2B version 0.9.6-distilled license - 13B version 0.9.7-dev license - 13B version 0.9.7-dev-fp8 license…

Excerpt from the card by LTX.io, licensed other.

Identity and Version

Repository: Lightricks/LTX-Video
Publisher: LTX.io
Task: Image to video
Modality: Other
Library: diffusers
Parameters: 1.9B parameters
Languages: en
Revision: 8984fa25007f376c1a299016d0957a37a2f797bb
First published: 2024-10-31
Last updated: 2025-07-16

Files and Weights

63 files, 254.1 GB in total. The weights are 27 files totalling 253.8 GB in safetensors.

Weights27 files · 253.8 GB

Configuration9 files · 99.7 KB

Tokenizer2 files · 812.3 KB

Documentation4 files · 69.2 KB

Other20 files · 297.0 MB

Repository1 file · 3.4 KB

Every file

File	Type	Size	SHA-256
ltx-video-2b-v0.9.1.safetensors	Weights	5.7 GB	a23200896c5e
ltx-video-2b-v0.9.5.safetensors	Weights	6.3 GB	720d15c9f19f
ltx-video-2b-v0.9.safetensors	Weights	9.4 GB	45369c2ae94e
ltxv-13b-0.9.7-dev-fp8.safetensors	Weights	15.7 GB	b281bbb53b76
ltxv-13b-0.9.7-dev.safetensors	Weights	28.6 GB	56b39a874ef9
ltxv-13b-0.9.7-distilled-fp8.safetensors	Weights	15.7 GB	d79f419b7203
ltxv-13b-0.9.7-distilled-lora128.safetensors	Weights	1.3 GB	c6004b2d7b29
ltxv-13b-0.9.7-distilled.safetensors	Weights	28.6 GB	ae3b07c28f19
ltxv-13b-0.9.8-dev-fp8.safetensors	Weights	15.7 GB	b281bbb53b76
ltxv-13b-0.9.8-dev.safetensors	Weights	28.6 GB	56b39a874ef9
ltxv-13b-0.9.8-distilled-fp8.safetensors	Weights	15.7 GB	111a3d07baa1
ltxv-13b-0.9.8-distilled.safetensors	Weights	28.6 GB	2c5f814744f0
ltxv-2b-0.9.6-dev-04-25.safetensors	Weights	6.3 GB	e6fb3fe995e2
ltxv-2b-0.9.6-distilled-04-25.safetensors	Weights	6.3 GB	94891bd4bd08
ltxv-2b-0.9.8-distilled-fp8.safetensors	Weights	4.5 GB	d6d8fa8ed3a9
ltxv-2b-0.9.8-distilled.safetensors	Weights	6.3 GB	76aa8c4786af
ltxv-spatial-upscaler-0.9.7.safetensors	Weights	505.0 MB	5b076031c6f8
ltxv-spatial-upscaler-0.9.8.safetensors	Weights	505.0 MB	5b076031c6f8
ltxv-temporal-upscaler-0.9.7.safetensors	Weights	523.9 MB	92ee7c34a060
ltxv-temporal-upscaler-0.9.8.safetensors	Weights	523.9 MB	92ee7c34a060
text_encoder/model-00001-of-00004.safetensors	Weights	5.0 GB	7a68b2c8c080
text_encoder/model-00002-of-00004.safetensors	Weights	5.0 GB	b8ed6556d750
text_encoder/model-00003-of-00004.safetensors	Weights	4.9 GB	c831635f8304
text_encoder/model-00004-of-00004.safetensors	Weights	4.2 GB	02a5f2d69205
transformer/diffusion_pytorch_model-00001-of-00002.safetensors	Weights	4.9 GB	8acd3e0bda74
transformer/diffusion_pytorch_model-00002-of-00002.safetensors	Weights	2.8 GB	03b3c822c31e
vae/diffusion_pytorch_model.safetensors	Weights	1.7 GB	265ca87cb5df
model_index.json	Configuration	412 B	—
scheduler/scheduler_config.json	Configuration	418 B	—
text_encoder/config.json	Configuration	781 B	—
text_encoder/model.safetensors.index.json	Configuration	19.9 KB	—
tokenizer/added_tokens.json	Configuration	2.6 KB	—
tokenizer/special_tokens_map.json	Configuration	2.5 KB	—
transformer/config.json	Configuration	500 B	—
transformer/diffusion_pytorch_model.safetensors.index.json	Configuration	72.1 KB	—
vae/config.json	Configuration	501 B	—
README.md	Documentation	21.1 KB	—
ltx-video-2b-v0.9.1.license.txt	Documentation	16.0 KB	—
ltx-video-2b-v0.9.5.license.txt	Documentation	16.1 KB	—
ltx-video-2b-v0.9.license.txt	Documentation	16.0 KB	—
LTX-Video-Open-Weights-License-0.X.txt	Other	14.5 KB	—
media/ltx-video_example_00001.gif	Other	8.0 MB	b679f14a09d2
media/ltx-video_example_00005.gif	Other	5.7 MB	87fdb9556c12
media/ltx-video_example_00006.gif	Other	132 B	ac92edd9c2e7
media/ltx-video_example_00007.gif	Other	132 B	68d15278b9d7
media/ltx-video_example_00010.gif	Other	6.2 MB	bcf1e084e936
media/ltx-video_example_00011.gif	Other	132 B	15b67e58e7bc
media/ltx-video_example_00013.gif	Other	9.0 MB	aa7eb790b43f
media/ltx-video_example_00014.gif	Other	132 B	ae7c3cdb08be
media/ltx-video_example_00015.gif	Other	132 B	af8e94d5b982
media/ltx-video_i2v_example_00001.gif	Other	9.3 MB	51e7f2ef92a9
media/ltx-video_i2v_example_00002.gif	Other	20.4 MB	0bd2c1314587
media/ltx-video_i2v_example_00003.gif	Other	9.8 MB	bb62a7934088
media/ltx-video_i2v_example_00004.gif	Other	15.7 MB	151cb985a162
media/ltx-video_i2v_example_00005.gif	Other	10.3 MB	6280efa40b66
media/ltx-video_i2v_example_00006.gif	Other	11.9 MB	da23e79524a6
media/ltx-video_i2v_example_00007.gif	Other	11.8 MB	9bcfe336e823
media/ltx-video_i2v_example_00008.gif	Other	14.7 MB	706368111eda
media/ltx-video_i2v_example_00009.gif	Other	16.8 MB	a9c13259e014
media/trailer.gif	Other	147.3 MB	fe193ca2f5d6
.gitattributes	Repository	3.4 KB	—
tokenizer/spiece.model	Tokenizer	791.7 KB	d60acb128cf7
tokenizer/tokenizer_config.json	Tokenizer	20.6 KB	—

License and Download

License: other
Access: Open weights, no gate
Download size: 253.8 GB

Download from LTX.io

Released by LTX.io through its official repository on Hugging Face.

Memory Requirements

Precision	Weights in memory
As published	253.8 GB
16-bit	3.8 GB
8-bit	1.9 GB
4-bit	1.0 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About LTX-Video

How much GPU memory does LTX-Video need?

About 4.6 GB at 16-bit and 1.2 GB at 4-bit: the weights (1.9B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run LTX-Video on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

What license is LTX-Video released under?

other, as its publisher declares it. Read the license text before commercial use.

Similar Models

Model · Image to video

Wan_2.2_ComfyUI_Repackaged

Comfy Org

Repackaged model files for ComfyUI. - https://huggingface.co/nvidia/ChronoEdit-14B-Diffusers - https://huggingface.co/Wan-AI/Wan2.2-Animate-14B - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-Control-Camera - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-Control - https://huggingface.co/alibaba-pai/Wan2.2-Fun-5B-Control - https://huggingface.co/alibaba-pai/Wan2.2-Fun-5B-InP - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-InP - https://huggingface.co/alibaba-pai/Wan2.2-VACE-Fun-A14B - https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B - https://huggingface.co/Wan-AI/Wan2.2-S2V-14B - https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B - https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B…

Open weights apache-2.0 diffusion-single-file

View model

Model · Image to video

LTX-2.5

LTX.io

LTX-2.5 is an open world model with open weights, built for local execution and fine-tuning. Its established use is generating synchronized, high-fidelity video and audio from text, image, and video inputs; applicability to emerging domains such as robotics and physical AI is developing. Full control and customization — self-host on your own infrastructure. No per-generation billing, no per-seat lock-in, no forced API dependency. Revenue is measured across the whole entity, including subsidiaries and affiliates under common control. The full, binding terms live in LICENSE. - Native multishot generation — generate connected scenes in a single pass: multiple shots that hold character…

Access requested at publisher other diffusion-single-file

View model

Model · Image to video

Minimax-h3-Turbo

Lightx2v

Please check our repository or the LightX2V MiniMax-H3 examples to reproduce the results. Please check the model specifications for more details. Try the MiniMax-H3 Turbo LoRA directly in LightX2V Studio: The Studio currently uses the FL2V 8-step v1.0 768p LoRA, which provides improved video and audio generation quality with 8-step inference. Integrate MiniMax-H3 Turbo into your application through the LightX2V API

Open weights apache-2.0 diffusers

View model

Model · Image to video

LTX-2.3

LTX.io

This model card focuses on the LTX-2.3 model, which is a significant update to the LTX-2 model with improved audio and visual quality as well as enhanced prompt adherence. LTX-2 was presented in the paper LTX-2: Efficient Joint Audio-Visual Foundation Model. If you want to dive in right to the code - it is available here. LTX-2.3 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution. LTX-2.3 is accessible right away via the API Playground. You can use the models - full, distilled, upscalers and any…

Open weights other diffusers

View model

Model · Image to video

MiniMax-H3-GGUF

Jay

This repository (Abiray/MiniMax-H3-GGUF) provides GGUF quantized versions and necessary component files for the MiniMax H3 model. MiniMax H3 is a general-purpose, omni-modal generative system that supports unified understanding of multimodal contexts composed of text, images, video, and audio. It can generate video with native stereo audio at resolutions up to 2K and durations of up to 15 seconds. If you are looking for a smaller model with the same great quality that fits better on consumer-tier GPUs, please check out the MiniMax-H3-Pruned-GGUF repository. The pruned architecture is compressed down to 8.9 GB – 21.6 GB, bringing MiniMax H3 execution directly to consumer hardware. This…

Open weights other

View model

Model · Image to video

LTX-2.3-fp8

LTX.io

This is the FP8 versions of the LTX-2.3 model. All information below is derived from the base model. This model card focuses on the LTX-2.3 model, which is a significant update to the LTX-2 model with improved audio and visual quality as well as enhanced prompt adherence. LTX-2 was presented in the paper LTX-2: Efficient Joint Audio-Visual Foundation Model. If you want to dive in right to the code - it is available here. LTX-2.3 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution. LTX-2.3 is…

Open weights other diffusers

View model