--- license: other license_name: ltx-2-community-license-agreement license_link: https://huggingface.co/Lightricks/LTX-2.3/blob/main/LICENSE language: - en tags: - text-to-video - image-to-video - audio-to-video - ltx-video - gguf - quantized - distilled - dit base_model: Lightricks/LTX-2.3 pipeline_tag: text-to-video --- # LTX-Video 2.3 (v1.1) 22B Distilled - GGUF This repository contains the **LTX-Video 2.3 (v1.1)** Distilled weights, quantized to **GGUF** format. GGUF offers highly efficient inference and excellent memory scaling, allowing you to run this heavy 22B parameter model on consumer hardware by splitting the workload between your GPU (VRAM) and CPU (System RAM). ## ⚡ Model Details - **Architecture:** LTX-Video 2.3 22B Distilled(v1.1) - **Parameter Count:** ~22B - **Format:** GGUF - **Special Feature:** Native Audio-Visual generation (DiT-based) ## 📦 Available Quantizations Choose the version that best fits your system's memory constraints. * **`LTX-2.3-22B-distilled-1.1-Q8_0.gguf`** (25.5 GB): Highest quality, nearly indistinguishable from unquantized. Requires significant RAM/VRAM. * **`LTX-2.3-22B-distilled-1.1-Q6_K.gguf`** (21.0 GB): Excellent balance of quality and size. Recommended for high-end GPUs. * **`LTX-2.3-22B-distilled-1.1-Q5_K_M.gguf`** (19.4 GB): Very good quality with a smaller footprint. * **`LTX-2.3-22B-distilled-1.1-Q4_K_M.gguf`** (17.8 GB): The standard recommendation for most users. Great trade-off between performance and visual fidelity. * **`LTX-2.3-22B-distilled-1.1-Q3_K_M.gguf`** (14.7 GB): Smallest footprint. Best for machines with limited memory, though minor visual degradation may occur. ## 🛠️ Usage & Implementation (ComfyUI) To use these GGUF files in **ComfyUI**, you will need a custom node suite that supports loading GGUF models (such as `ComfyUI-GGUF`). ## 📜 License This model is released under the **LTX-2 Community License Agreement** by Lightricks.
