// HACKER NEWS ā CYBERSECURITY
LFM2.5 2.6B model competitive with 4x larger models
How to use LiquidAI/LFM2.5-2.6B with Docker Model Runner:
LFM2.5-2.6B is part of LFM2.5, a family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with a 128K context window and agentic post-training.
Find more information about LFM2.5-2.6B in our blog post.
š» Demos: Try LFM2.5-2.6B's agentic capabilities in a Hugging Face space without any setup:
Research Agent in your browser: helps you research a specific question and generates a summary
LFM2.5-2.6B is a general-purpose text-only model with the following features:
We recommend using it for agentic workloads, tool use, data extraction, RAG, and long-context workflows. It is not recommended for agentic coding and knowledge-heavy tasks.
LFM2.5 uses a ChatML-like format. See the Chat Template documentation for details. Example:
You can use tokenizer.apply_chat_template() to format your messages automatically.
š” Note: LFM2.5-2.6B is a pure reasoning model that always thinks before it answers. It adds a tag directly in the chat template when starting an assistant answer.
See the Tool Use documentation for the full guide. Example: