AgentsMachine Learning5 min reading time

Deploy local agents everywhere with LFM2.5-2.6B

Hugging Face
Read full post
LFM2.5-2.6B is a compact AI model designed for on-device agents, supporting tool use and multi-step workflows efficiently on everyday hardware like laptops and phones. It achieves performance comparable to models four times its size through advanced training including agentic reinforcement learning. The model enables private, scalable deployment without cloud inference costs.

More in Agents

Meta Announces Muse AI Agent for Personal Tasks and Organization

Covered by 11 sources

Introducing the Agents API

Covered by 3 sources
Agents4 min read

Amazon makes its agentic AI platform Quick generally available for desktop on Windows and macOS

Covered by 2 sources