LFM2.5-24B-A2B: Built for Fast On-Device Agents
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.
Summary
LFM2.5-24B-A2B is a new open-weight reasoning model designed for efficient performance on devices, featuring 2 billion active parameters. It surpasses the capabilities of the Qwen3.6-35B-A3B model in a competitive benchmark, indicating significant advancements in on-device AI processing.
Comments (81 of ) ⌛