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.
Try NowEfficient edge moe inference
On-device high-quality text
Low-compute budget task
32,768 tokens
32,768 tokens
$0.01 per 1M tokens
$0.02 per 1M tokens
$15 per 1K calls
$0.19 per 1K calls