NVDA 155.46 ▼0.44%GOOGL 280.20 ▼1.24%MSFT 506.24 ▼2.27%AMD 503.41 ▼0.17%INTC 55.17 ▼0.54%TSMC 359.69 ▼3.68%AMZN 257.89 ▲0.05%META 618.87 ▼1.20%AAPL 351.91 ▼0.25%PLTR 156.56 ▼2.39%
Markets at last close

Models

Liquid AI targets local and cloud deployment with specialized models

·1 min read

Liquid AI offers a family of foundation models designed for deployment across laptops, phones, edge devices and cloud infrastructure. The company emphasizes lightweight, customizable models and compute efficiency, with separate offerings for text, vision-language, audio, decision-making and specialized tasks.

Its decision models handle classification, routing and scoring, returning calibrated probabilities across a fixed set of outcomes through an API call. Audio models support audio and text generation for responsive conversations, while omni models accept and generate text, images and audio without combining separate pipelines. Smaller nano models target specific tasks and knowledge, including embedding, information extraction and personal information detection.

Local deployment options include GGUF, MLX and ONNX builds that run without an API key. Developers can also use an OpenAI-compatible endpoint or serve models on their own GPU infrastructure. Every Liquid Foundation Model is free to download, run and fine-tune, including commercially, until the company using it passes $10M in annual revenue.

Originally reported by liquid.aiRead the source →
Related coverage