The FASTEST local AI video generator
Community-compressed GGUF versions of LTX 2.5 for low VRAM; the smallest Q3 small is 12.6 GB. The creator loads it with the Unet Loader GGUF node and shows the result is acceptable.
L2
LTX 2.5 GGUF
Community GGUF-quantized builds of the LTX 2.5 video model for running on low-VRAM GPUs, e.g. in ComfyUI.
Updated EU status checked Last shown
LTX 2.5 GGUF at a glance
- What is LTX 2.5 GGUF?
- LTX 2.5 GGUF is a model. Community GGUF-quantized builds of the LTX 2.5 video model for running on low-VRAM GPUs, e.g.
- Does LTX 2.5 GGUF work in the EU?
- Available in the EU. Downloadable community weights that run locally, so they are usable in the EU; no explicit EU restriction found, though the upstream LTX 2.5 license was not verified. Last verified 14 Nov 2026.
- How much does LTX 2.5 GGUF cost?
- Open source. Free to download community weights; run locally on your own hardware.
- Where was LTX 2.5 GGUF shown?
- In 1 creator video by AI Search. Most recently by AI Search on 18 Aug 2026, at 12:48 in “The FASTEST local AI video generator”.
Sources: creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
About
LTX 2.5 GGUF refers to community-made quantized versions of Lightricks' LTX 2.5 video generation model, converted to the GGUF format so they need less VRAM. Several quantization levels are shared; according to a YouTube creator (AI Search), the smallest, Q3 small, is about 12.6 GB.
The files are loaded in ComfyUI through a GGUF loader node (the creator uses the Unet Loader GGUF node). The creator reports that output quality from the heavily compressed Q3 variant is acceptable, though lower-bit quantization generally trades some quality for memory savings.
These are unofficial conversions, not a vendor release. Exact repositories, authors, and licensing were not available from the provided material; licensing likely follows the upstream LTX 2.5 model terms, which should be checked before use.
Key features
- GGUF quantizations of LTX 2.5 for low-VRAM GPUs
- Smallest Q3 small variant is about 12.6 GB
- Loads in ComfyUI via the Unet Loader (GGUF) node
- Community-made, unofficial conversions
1 moment
As seen on YouTube
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Keep exploring
Similar AI tools
Closest neighbours by meaning, not just by category.
QI
Qwen Image 2.1 GGUF
Model · Abiray
Community GGUF quantizations of Qwen-Image-2.1 for low-VRAM text-to-image and image editing in ComfyUI.
Available in EUPlatforms & Infra
20 Sept 2026Open source
MH
MiniMax H3 GGUFs
Model · Unsloth
GGUF quantizations of MiniMax-H3 video-with-audio generation model, for stable-diffusion.cpp and Unsloth.
Available in EUPlatforms & Infra
7 Aug 2026Open source
L2
LTX 2.5 Upscaler with MiniMax
App
Community ComfyUI workflow that generates video with MiniMax and upscales it using the LTX 2.5 spatial upscaler.
UnverifiedVideo Generation
Release date n/aFree
L2
LTX 2.5
Model · Lightricks
Open-weights Lightricks video model with native audio, multi-shot generation, auto duration and up to 4K output.
Available in EUVideo Generation
23 Jul 2026Open source
WA
Wan2GP
App
Open-source local web app for running video, image, audio, music and 3D generative models on low-VRAM GPUs.
Available in EUPlatforms & Infra
27 Feb 2025Open source
CO
ComfyUI
App · Comfy Org
Node-based visual AI engine for running image, video, audio and 3D generation workflows locally, in the cloud or via API.
Available in EUPlatforms & Infra
17 Jan 2023Open source