
LTX-2.3 NVFP4 Audio-Video Generation on Modular
LTX-2.3 NVFP4 is a quantized 22B DiT-based audio-video diffusion model from Lightricks. It generates synchronized video and audio, with support for text, image, video, and audio-conditioned generation workflows.
Example Usage
- Developed byLightricks
- Model familyLightricks/LTX-2.3-nvfp4
- Input ModalityText
- Output ModalityAudio, Video
- Total Params22B
- PrecisionNVFP4
- Deployment optionsShared, Dedicated, Self-hosted
Why choose LTX-2.3 on Modular?
Run leading open models with strong default performance and the ability to optimize down to the kernel — extracting more from every GPU.
Deploy efficiently across NVIDIA and AMD hardware to reduce GPU count, increase throughput, and avoid expensive closed-model licensing.
Integrate through an OpenAI-compatible endpoint, swap models freely, and scale across clouds or hardware without redesigning your application stack.
🔥 Trending models

DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks. Alongside these gains, the model reduces task execution time and output length, enabling users to complete tasks faster and at lower cost and advancing the performance–cost Pareto frontier across multiple agent harnesses.

GLM-5.3-Flash is the first natively multimodal model in Z.ai's GLM-5 series, with 320B total parameters and 18B active. A hybrid architecture combining sparse and linear attention cuts attention compute and KV cache by 3.0x and 4.4x against GLM-5.3, supporting a 1M-token context window at low serving cost for visual coding and agentic workflows.

MiniMax M3.1 Flash delivers a generational leap in agentic tasks, coding, Computer Use and cybersecurity, while making online inference nearly three times faster and reducing usage costs by 70%. M3.1 Flash’s inference efficiency has improved through more aggressive sparsity. In everyday use, output speeds can reach 200+ TPS (tokens per second), with median (P50) speeds consistently reaching 170+ TPS.
Similar models

Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. The model is designed to be used by developers building AI-powered applications, including agentic and tool-use systems, coding assistants, chatbots, and retrieval-augmented generation systems, and is suitable for general-purpose conversational use, instruction-following, and other natural language and multimodal tasks.
Get started with Modular
Schedule a demo of Modular and explore a custom end-to-end deployment built around your models, hardware, and performance goals.
Distributed, large-scale online inference endpoints
Highest-performance to maximize ROI and latency
Deploy in Modular cloud or your cloud
View all features with a custom demo

Book a demo
Talk with our sales lead Adam!
30min demo. Evaluate with your workloads. Ask us anything.
Book a demo for a personalized walkthrough of Modular in your environment. Learn how teams use it to simplify systems and tune performance at scale.
Custom 30 min walkthrough of our platform
Cover specific model or deployment needs
Flexible pricing to fit your specific needs

Book a demo
Talk with our sales lead Jay!
Run any open source model in 5 minutes, then benchmark it. Scale it to millions yourself (for free!).
Install Mojo and get up and running in minutes. A simple install, familiar tooling, and clear docs make it easy to start writing code immediately.

