LFM2-24B-A2B: Scaling Up the LFM2 Architecture

Keyword: Energy Consumption

Publisher: Liquid.ai

Published: Apr 30, 2026

Today, we release an early checkpoint of LFM2-24B-A2B, our largest LFM2 model. This sparse Mixture of Experts (MoE) model has 24 billion total parameters with 2 billion active per token, showing that… [+5800 chars]

Read Full Story ↗