Back to News
Liquid AI•June 25, 2026
LFM2.5-Encoder-230M
Open Source
encoder
masked-lm
multilingual
on-device
### TL;DR
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 Insights & Metrics
Pricing
Free to download, run, and fine-tune
Cost structure
Version
2.5
Current release version
Hardware
Compatible with standard CPU/GPU environments; supports Flash Attention 2 for enhanced efficiency on supported GPUs
Compute requirements
Category
Open Source
Licensing model
Region
United States
Primary region
Key Features
- Multilingual support across 15 languages
- 8,192 token context window
- Optimized for on-device and WebGPU deployment
- Full bidirectional attention for masked language modeling
- High throughput performance comparable to larger encoders
Discussion
0
Upvotes
0
Downvotes
0 reviews
Sign in to leave a review
Reviews
No reviews yet. Be the first to review!