LFM2-8B-A1B is an efficient on-device Mixture-of-Experts (MoE) model from Liquid AI’s LFM2 family, built for fast, high-quality inference on edge hardware. It uses 8.3B total parameters with only ~1.5B active per token, delivering strong performance while keeping compute and memory usage low—making it ideal for phones, tablets, and laptops.
Modalities
Context
8K
Released
Oct 20, 2025
Token volume and request traffic to this model over time.
LFM2-8B-A1B is an efficient on-device Mixture-of-Experts (MoE) model from Liquid AI’s LFM2 family, built for fast, high-quality inference on edge hardware. It uses 8.3B total parameters with only ~1.5B active per token, delivering strong performance while keeping compute and memory usage low—making it ideal for phones, tablets, and laptops.
LFM2-8B-A1B has a 8,192 token context window.
LFM2.5-2.6B (free) is another text model from Liquid.
LFM2-8B-A1B was released on October 20, 2025.