LFM2.5-24B-A2B: Built for Fast On-Device Agents | Blog | Liquid AIWeb Page - www.liquid.ai
liquid.ai

LFM2.5-24B-A2B: Built for Fast On-Device Agents | Blog | Liquid AI

LFM2.5-24B-A2B: an open-weight 24B reasoning model with 2B active parameters, built for fast, private on-device agents. Beats Qwen3.6-35B-A3B on LiveClaw.

If the page stays blank, open it in a new tab. Your Weird rating still works from the top bar.

Open source