← all releases
Liquid AI·Jun 25, 2026·v2.5·open source

LFM2.5-Encoder-230M

LFM2.5-Encoder-230M is a lightweight, multilingual bidirectional encoder built on the LFM2 hybrid architecture. It is designed for high-performance, low-latency tasks such as text classification, retrieval, and PII detection, optimized for on-device and browser-based deployment.

encodermasked-lmmultilingualon-device
overview

LFM2.5-Encoder-230M is a lightweight, multilingual bidirectional encoder built on the LFM2 hybrid architecture. It is designed for high-performance, low-latency tasks such as text classification, retrieval, and PII detection, optimized for on-device and browser-based deployment.

key features
  • 01Multilingual support across 15 languages
  • 028,192 token context window
  • 03Optimized for on-device and WebGPU deployment
  • 04Full bidirectional attention for masked language modeling
  • 05High throughput performance comparable to larger encoders
related productsbrowse all →