Post #233966 284 Oct 15, 2026, 00:07 UTC LFM2.5-24B-A2B: Built for Fast On-Device AgentsArticle, Comments Liquid AI LFM2.5-24B-A2B: Built for Fast On-Device Agents | Blog 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. ❤ 3 🖕 1