Skip to main content
← Back to Text Models LFM2.5-230M is Liquid AI’s smallest LFM2.5 text model, designed for edge devices with the tightest memory and compute budgets. Built on the LFM2.5 architecture, it is tuned for data extraction and lightweight on-device agentic tasks such as tool calling. It is not recommended for reasoning-heavy workloads like advanced math, code generation, or creative writing — use LFM2.5-350M or a larger model for those.

​
Specifications

PropertyValue
Parameters230M
Context Length32K tokens
ArchitectureLFM2.5 (Dense)

Ultra-Light

Smallest LFM2.5 footprint for the tightest memory budgets

Data Extraction

Powers large-scale extraction pipelines

Edge-Ready

Fast on-device agentic tasks and tool calling

​
Quick Start