> [!Note] > This repository corresponds to the 12B **instruction-tuned** version of the Gemma 3 model using Quantization Aware Training (QAT). > > **The checkpoint in this repository is unquantized, please make sure to quantize with Q4_0 with your favorite tool** > > Thanks to QAT, the model is able to preserve similar quality as `bfloat16` while significantly reducing the memory requirements > to load the model. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. These models were trained on a dataset of text data that includes a wide variety of sources. The 27B model was trained with 14 trillion tokens, the 12B model was trained with 12 trillion tokens, 4B model was trained with 4 trillion tokens and 1B with 2 trillion tokens. Here are the key components:
This model card focuses on the LTX-2 model, as presented in the paper LTX-2: Efficient Joint Audio-Visual Foundation Model. The codebase is available here. LTX-2 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. - **Developed by:** Lightricks - **Model type:** Diffusion-based audio-video foundation model - **Language(s):** English
This is a camera-motion control **LoRA** trained to bias generations toward a **dolly-left** camera move (camera translates laterally to the left, revealing content on the left side of the scene and changing parallax) on top of an **LTX-2 19B** base video model. To get the best results with Motion Camera LoRAs, describe the **destination of the movement** and the **hidden parts of the scene** so the model knows what to reveal as the frame shifts. For a dolly-left shot, explicitly mention what should come into view on the **left side** during the move (e.g., the far-left side of a room, objects/people positioned off-frame to the left, background structures that become visible due to parallax). This gives the model a visual “map” of what exists as the camera slides left.
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.
**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.** 💾💾
**This is the NVFP4 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. 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.
