• Research
  • Build with LEAP
Connect

Building the fastest, most compute-efficient, and capable foundation models so intelligence can live anywhere.

Est. 2023

Models

  • Liquid Foundation Models
  • LFM2 VL
  • LFM2.5
  • Liquid Nanos
  • Model Playground
  • Hugging Face

Platforms

  • Liquid Edge AI Platform (LEAP)
  • Apollo
  • Documentation

Industries

  • Automotive
  • Consumer electronics
  • E-commerce
  • Financial services
  • Healthcare
  • Industrial
  • Defense

Research

  • Liquid Labs
  • Automated Foundation Model Design
  • Blog

Company

  • About
  • Careers
  • News
  • FAQ
  • Contact
  • Shoutouts

Developer Resources

  • Demos
  • Documentation
  • Hackathons
  • Discord
  • GitHub

© 2026 Liquid AI, Inc.

  • Terms
  • Privacy
  • Press

News/Models

News and Updates

AllModelsCase studiesCompany newsResearch
LFM2.5-230M: Built to Run Anywhere
JUN 25, 2026Models

LFM2.5-230M: Built to Run Anywhere

  • 06.18.2026Models
    06.18.2026ModelsLFM2.5 Retrievers: Bi-directional LFMs for Fast Multilingual Search
  • 05.28.2026Models
    05.28.2026ModelsLFM2.5-8B-A1B: An Even Better On-Device Mixture of Experts
  • 04.08.2026Models
    04.08.2026ModelsLFM2.5-VL-450M: Structured Visual Intelligence, Edge to Cloud
  • 03.31.2026Models
    03.31.2026ModelsLFM2.5-350M: No Size Left Behind
  • 03.05.2026Models
    03.05.2026ModelsNo Cloud, No Waiting: Tool-Calling Agents on Consumer Hardware with LFM2-24B-A2B
  • 02.24.2026Models
    02.24.2026ModelsLFM2-24B-A2B: Scaling Up the LFM2 Architecture
  • 01.20.2026Models
    01.20.2026ModelsLFM2.5-1.2B-Thinking: On-Device Reasoning Under 1GB
  • 01.07.2026Models
    01.07.2026ModelsThe Future of Meeting Summarization: Local, Fast, Private, and Fully Secure
  • 01.05.2026Models
    01.05.2026ModelsIntroducing LFM2.5: The Next Generation of On-Device AI
  • 10.28.2025Models
    10.28.2025ModelsLFM2-ColBERT-350M: One Model to Embed Them All
  • 10.22.2025Product
    10.22.2025ProductHow Liquid AI Uses ExecuTorch to Power Efficient, Flexible On-Device Intelligence
  • 10.22.2025Models
    10.22.2025ModelsLFM2-VL-3B: A New Efficient Vision-Language for the Edge
  • 10.07.2025Models
    10.07.2025ModelsLFM2-8B-A1B: An Efficient On-device Mixture-of-Experts
  • 10.01.2025Models
    10.01.2025ModelsLFM2-Audio: An End-to-End Audio Foundation Model
  • 09.25.2025Models
    09.25.2025ModelsIntroducing Liquid Nanos — frontier‑grade performance on everyday devices