Introducing LFM-7B: Setting New Standards for Efficient Language Models
The world’s best-in-class English, Arabic, and Japanese model, native in French, German, and Spanish, optimized to be the substrate for private enterprise chat, code, fast instruction following, and agentic workflows.
Today, we release LFM-7B, a new best-in-class language model. LFM-7B is designed for exceptional chat capabilities, including languages like Arabic and Japanese. Powered by the Liquid Foundation Model (LFM) architecture, it exhibits unique features like low memory footprint and fast inference speed. This makes it cost-efficient to fine-tune for specific use cases (such as smart chatbots and document generation) and to deploy on-premises or directly on devices.
LFM-7B is specifically optimized for response quality, accuracy, and usefulness. To assess its chat capabilities, we leverage a diverse frontier LLM jury to compare responses generated by LFM-7B against other models in the 7B-8B parameter category. It allows us to reduce individual biases and produce more reliable comparisons.
We compared answers to English prompts that include curated business use cases such as following instructions, questions from Arena-Hard-Auto (Li et al.), and real-world conversations (Zheng et al.). Thanks to our comprehensive preference alignment process, LFM-7B outperforms every LLM in the same size category.
