# Liquid AI says Hugging Face tuned LFM2.5-24B-A2B for agentic work

> Original title: LFMs are built to be customized. We think specialized intelligence is what enables more than half of enterprise AI usecases with predicab...

- Source: Liquid AI
- Published: 2026-10-30T17:06:22.000Z
- Bad Influence: https://badinfluence.news/items/ju0s72x4k95xuqvb65nps91lb
- Original: https://x.com/liquidai/status/2116215143281648029

## Summary

Liquid AI says the Hugging Face team tuned its LFM2.5-24B-A2B model for more efficient agentic behavior in open-source harnesses. Hugging Face released LoRA adapters for Pi and Claude Code, which cut tool calls by up to 40% on Pi.

## Post

LFMs are built to be customized. We think specialized intelligence is what enables more than half of enterprise AI usecases with predicable economics.

This is an incredible work by the @huggingface team on tuning our LFM2.5-24B-A2B for more efficient agentic behavior in opensource harnesses. 🤗

## Quoted post @yb2698

> LFM2.5-24B adapters for Pi and Claude Code!
> 
> We release LoRA adapters trained on top of LFM2.5-24B - more efficient agentic development on opensource harnesses (up to 40% less tool calls on Pi!)!
> 
> https://huggingface.co/collections/harness-hub/lfm25-24b-harness-adapters

https://x.com/yb2698/status/2116114294383464836