Liquid AI open-sources small-scale multimodal models for direct image-to-JSON data extraction

KuCoinFlash

Release Time: 06/05/2026 11:24:51

Summary

Liquid AI has open-sourced two compact multimodal models, LFM2.5-VL-1.6B-Extract and LFM2.5-VL-450M-Extract, for direct image-to-JSON data extraction. Available under the LFM Open License v1.0, these models are optimized for edge devices and deliver strong performance in document scanning and industrial inspection. The 1.6B model matches the performance of 4B-scale models, while the 450M model rivals 2B-scale models. These tools can enhance CFT efforts by improving data transparency. The models are now available for download on Hugging Face.

ME AI News: According to monitoring by Beating, Liquid AI has open-sourced two lightweight multimodal models: LFM2.5-VL-1.6B-Extract and LFM2.5-VL-450M-Extract. These new models are specifically optimized for structured data extraction from images, enabling direct conversion of images into JSON-formatted data on-device based on user-specified field lists, eliminating the need for traditional multimodal models to generate full text before secondary parsing. The models are available in two parameter sizes: 1.6 billion (1.6B) and 450 million (450M), and are released under the LFM Open License v1.0. Official evaluations show superior performance in scenarios such as document scanning, in-vehicle cabin understanding, and industrial inspection. In benchmark tests, the 1.6B model matches the performance of general-purpose multimodal models with 4 billion (4B) parameters, while the 450M model rivals 2 billion (2B) parameter models. On the deployment side, the models have been optimized for various smart hardware and edge device SoCs, enabling offline deployment in on-device scenarios like in-vehicle cabin understanding, document scanning, and industrial inspection. Liquid AI has now made the model weights available for download on the Hugging Face platform. (Source: MLion)

Source:Show original

Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information. Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.