SAVRN
Search Contact SAVRN

Open-weight model · Image to video

LTX-2.3-GGUF

by Unsloth AI unsloth/LTX-2.3-GGUF

This is a GGUF quantized version of LTX-2.3. unsloth/LTX-2.3-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. - Important layers are upcasted to higher precision. - Uses tooling from ComfyUI-GGUF by city96.

Parameters—
Context—
Weights1.1 TB
Licenseother
AccessOpen weights
Monthly Downloads283.8k

Model Card

This is a GGUF quantized version of LTX-2.3. unsloth/LTX-2.3-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. - Important layers are upcasted to higher precision. - Uses tooling from ComfyUI-GGUF by city96. There are two sets of GGUF's published. One for the dev model and one for the distilled. The distilled model is optimized for few step generation, think 4-8 steps. dev on the other hand needs more steps at least 20, but you get better outputs. The distilled variant is useful as a drafting model or a refining model. In fact the workflow published below, uses the distilled lora on top of the dev model to refine the intial output. Download the mp4 in the repo and open it with…

Excerpt from the card by Unsloth AI, licensed other.

Identity and Version

Repository
unsloth/LTX-2.3-GGUF
Publisher
Unsloth AI
Task
Image to video
Modality
Other
Library
ggml
Parameters
Not stated by the source
Languages
en, de, es, fr, ja, ko, zh, it
Revision
96e8ed4925ead3db9ff4d0084f165ef6a74f28d0
First published
2026-03-05
Last updated
2026-04-20

Files and Weights

74 files, 1.1 TB in total. The weights are 69 files totalling 1.1 TB in gguf, safetensors.

Weights69 files · 1.1 TB
Documentation2 files · 30.7 KB
Other2 files · 4.9 MB
Repository1 file · 6.5 KB
Every file
FileTypeSizeSHA-256
distilled-1.1/ltx-2.3-22b-distilled-1.1-BF16.ggufWeights42.0 GB 74acbe938ed0
distilled-1.1/ltx-2.3-22b-distilled-1.1-F16.ggufWeights42.0 GB b0a2484f218d
distilled-1.1/ltx-2.3-22b-distilled-1.1-Q2_K.ggufWeights7.9 GB 3066a3e36232
distilled-1.1/ltx-2.3-22b-distilled-1.1-Q3_K_M.ggufWeights10.6 GB f58cbbe86bff
distilled-1.1/ltx-2.3-22b-distilled-1.1-Q3_K_S.ggufWeights9.7 GB 4449208e0613
distilled-1.1/ltx-2.3-22b-distilled-1.1-Q4_0.ggufWeights12.7 GB 1e6aa3f8506f
distilled-1.1/ltx-2.3-22b-distilled-1.1-Q4_1.ggufWeights13.8 GB baf0cf7aa332
distilled-1.1/ltx-2.3-22b-distilled-1.1-Q4_K_M.ggufWeights14.2 GB 5d09efdc0b8e
distilled-1.1/ltx-2.3-22b-distilled-1.1-Q4_K_S.ggufWeights13.0 GB f9e2b72221a9
distilled-1.1/ltx-2.3-22b-distilled-1.1-Q5_0.ggufWeights15.3 GB 893fade80017
distilled-1.1/ltx-2.3-22b-distilled-1.1-Q5_1.ggufWeights16.3 GB 6d6ad9f6ed14
distilled-1.1/ltx-2.3-22b-distilled-1.1-Q5_K_M.ggufWeights15.9 GB 5be111c2880b
distilled-1.1/ltx-2.3-22b-distilled-1.1-Q5_K_S.ggufWeights15.0 GB 3df4bdbe324a
distilled-1.1/ltx-2.3-22b-distilled-1.1-Q6_K.ggufWeights17.8 GB ece6e49954f6
distilled-1.1/ltx-2.3-22b-distilled-1.1-Q8_0.ggufWeights22.8 GB 813fd61eecf3
distilled-1.1/ltx-2.3-22b-distilled-1.1-UD-Q2_K.ggufWeights10.9 GB e8e61887211d
distilled-1.1/ltx-2.3-22b-distilled-1.1-UD-Q3_K_M.ggufWeights13.4 GB 53e9c48d0acc
distilled-1.1/ltx-2.3-22b-distilled-1.1-UD-Q4_K_M.ggufWeights16.4 GB 906beb54de87
distilled-1.1/ltx-2.3-22b-distilled-1.1-UD-Q5_K_M.ggufWeights18.2 GB d62cef1062b8
distilled/ltx-2.3-22b-distilled-BF16.ggufWeights42.0 GB af36517527eb
distilled/ltx-2.3-22b-distilled-F16.ggufWeights42.0 GB 62024e322f79
distilled/ltx-2.3-22b-distilled-Q2_K.ggufWeights8.3 GB b6362019297d
distilled/ltx-2.3-22b-distilled-Q3_K_M.ggufWeights10.8 GB 388614a12f3d
distilled/ltx-2.3-22b-distilled-Q3_K_S.ggufWeights9.9 GB 1afe1a733d52
distilled/ltx-2.3-22b-distilled-Q4_0.ggufWeights12.7 GB e2e8aa26046b
distilled/ltx-2.3-22b-distilled-Q4_1.ggufWeights13.8 GB 648879d77a0c
distilled/ltx-2.3-22b-distilled-Q4_K_M.ggufWeights14.3 GB 4e4459bee041
distilled/ltx-2.3-22b-distilled-Q4_K_S.ggufWeights13.1 GB 7e324537df35
distilled/ltx-2.3-22b-distilled-Q5_0.ggufWeights15.3 GB 4ee6ad804677
distilled/ltx-2.3-22b-distilled-Q5_1.ggufWeights16.3 GB ac5e5561185e
distilled/ltx-2.3-22b-distilled-Q5_K_M.ggufWeights16.1 GB 3b68bda1f50d
distilled/ltx-2.3-22b-distilled-Q5_K_S.ggufWeights15.2 GB 83ec9a84c1f8
distilled/ltx-2.3-22b-distilled-Q6_K.ggufWeights17.8 GB f32d8ba82958
distilled/ltx-2.3-22b-distilled-Q8_0.ggufWeights22.8 GB ed3be2737377
distilled/ltx-2.3-22b-distilled-UD-Q2_K.ggufWeights9.3 GB a93999b48942
distilled/ltx-2.3-22b-distilled-UD-Q3_K_M.ggufWeights13.2 GB 789a9f3737ae
distilled/ltx-2.3-22b-distilled-UD-Q3_K_S.ggufWeights11.2 GB ad234e7f48ca
distilled/ltx-2.3-22b-distilled-UD-Q4_K_M.ggufWeights16.3 GB 451ef931569f
distilled/ltx-2.3-22b-distilled-UD-Q4_K_S.ggufWeights14.1 GB 1d85fee19311
distilled/ltx-2.3-22b-distilled-UD-Q5_K_M.ggufWeights18.0 GB 97f841ead342
distilled/ltx-2.3-22b-distilled-UD-Q5_K_S.ggufWeights16.2 GB 31bff1672fc8
ltx-2.3-22b-dev-BF16.ggufWeights42.0 GB 42065145779f
ltx-2.3-22b-dev-F16.ggufWeights42.0 GB e01c7dc7ba1b
ltx-2.3-22b-dev-Q2_K.ggufWeights8.3 GB 67c2b4981eef
ltx-2.3-22b-dev-Q3_K_M.ggufWeights10.8 GB 9a8d25231b4c
ltx-2.3-22b-dev-Q3_K_S.ggufWeights9.9 GB 8d47db128c96
ltx-2.3-22b-dev-Q4_0.ggufWeights12.7 GB 792af9088793
ltx-2.3-22b-dev-Q4_1.ggufWeights13.8 GB b39dab14c3b4
ltx-2.3-22b-dev-Q4_K_M.ggufWeights14.3 GB e053e3d7827f
ltx-2.3-22b-dev-Q4_K_S.ggufWeights13.1 GB 3f7cb55f419b
ltx-2.3-22b-dev-Q5_0.ggufWeights15.3 GB 1ff0ab385a9a
ltx-2.3-22b-dev-Q5_1.ggufWeights16.3 GB 7c99d04a35e9
ltx-2.3-22b-dev-Q5_K_M.ggufWeights16.1 GB 532ff9b844e0
ltx-2.3-22b-dev-Q5_K_S.ggufWeights15.2 GB 0904cf86b5d6
ltx-2.3-22b-dev-Q6_K.ggufWeights17.8 GB 22593c668cbe
ltx-2.3-22b-dev-Q8_0.ggufWeights22.8 GB c4e78967e6c6
ltx-2.3-22b-dev-UD-Q2_K.ggufWeights9.5 GB 890f5d653b22
ltx-2.3-22b-dev-UD-Q3_K_M.ggufWeights13.5 GB b7f0be5ede20
ltx-2.3-22b-dev-UD-Q3_K_S.ggufWeights11.4 GB 821295b91bca
ltx-2.3-22b-dev-UD-Q4_K_M.ggufWeights16.5 GB a6983fcf16cd
ltx-2.3-22b-dev-UD-Q4_K_S.ggufWeights14.2 GB 727b8f39f6ea
ltx-2.3-22b-dev-UD-Q5_K_M.ggufWeights18.3 GB 191b06ba97d2
ltx-2.3-22b-dev-UD-Q5_K_S.ggufWeights16.3 GB f683f579042c
text_encoders/ltx-2.3-22b-dev_embeddings_connectors.safetensorsWeights2.3 GB a5c5148788d8
text_encoders/ltx-2.3-22b-distilled_embeddings_connectors.safetensorsWeights2.3 GB c61cbb396e2a
vae/ltx-2.3-22b-dev_audio_vae.safetensorsWeights364.9 MB d7711812d938
vae/ltx-2.3-22b-dev_video_vae.safetensorsWeights1.5 GB 8732bb70cf43
vae/ltx-2.3-22b-distilled_audio_vae.safetensorsWeights364.9 MB 3cd6a6eb8cb2
vae/ltx-2.3-22b-distilled_video_vae.safetensorsWeights1.5 GB e68d6d8f8a42
LICENSEDocumentation21.4 KB —
README.mdDocumentation9.3 KB —
ltx2.3-open.pngOther2.3 MB ab52a78cb26a
unsloth_flowers.mp4Other2.6 MB e5b4c7638cf3
.gitattributesRepository6.5 KB —

License and Download

License
other
Access
Open weights, no gate
Download size
1.1 TB
Download from Unsloth AI

Released by Unsloth AI through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published1.1 TB

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

Questions About LTX-2.3-GGUF

What license is LTX-2.3-GGUF 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