AI News

Liquid AI Releases LFM2.5-Encoder-230M and LFM2.5-Encoder-350M: Bidirectional Encoders That Stay Fast at 8K Context on CPU

Low Severity Global
Date Occurred Jul 29, 2026 09:38 UTC
Event Type AI News
Source AI News
Recorded Jul 29, 2026
Full Description

<p>Liquid AI released two open-weight bidirectional encoders, LFM2.5-Encoder-230M and LFM2.5-Encoder-350M. Both carry an 8,192-token context and are built on the LFM2 hybrid backbone. The 350M ranks f

Original Source
https://www.marktechpost.com/2026/07/29/liquid-ai-releases-lfm2-5-encoder-230m-and-lfm2-5-encoder-350m-bidirectional-encoders-that-stay-fast-at-8k-context-on-cpu/
Event Metadata
  • ID #19614
  • Type AI News
  • Region Global
  • Severity Low
  • Indexed Jul 29, 2026
Quick Actions
Back to Events View on Globe Read Original Article

Related Events

Fast Metals is treating waste with more waste to extract critical minerals
Jul 29, 2026 Low
OpenAI report links coding agents to faster science software builds
Jul 29, 2026 Low
Google AI Overviews become more common in search
Jul 29, 2026 Low United States
Liquid AI Releases LFM2.5-Encoder-230M and LFM2.5-Encoder-350M: Bidirectional Encoders That Stay Fast at 8K Context on CPU
Jul 29, 2026 Low
Why Goodfire’s block-sparse featururizers are a breakthrough in AI interpretability
Jul 29, 2026 Low Anguilla
Building Non-Interactive Agentic Coding Workflows with Moonshot AI’s Kimi CLI, JSONL Streaming, Testing, and Session Memory
Jul 28, 2026 Low Anguilla