NewsModels

News and Updates

AUG 4, 2026Models

LFM2.5-2.6B: Deploy Agents Everywhere

08.04.2026ModelsLFM2.5-2.6B: Deploy Agents Everywhere
07.28.2026ModelsLFM2.5-Encoders: Fast at Long Context, Even on CPU
06.25.2026ModelsLFM2.5-230M: Built to Run Anywhere
06.18.2026ModelsLFM2.5 Retrievers: Bi-directional LFMs for Fast Multilingual Search
05.28.2026ModelsLFM2.5-8B-A1B: An Even Better On-Device Mixture of Experts
04.08.2026ModelsLFM2.5-VL-450M: Structured Visual Intelligence, Edge to Cloud
03.31.2026ModelsLFM2.5-350M: No Size Left Behind
03.05.2026ModelsNo Cloud, No Waiting: Tool-Calling Agents on Consumer Hardware with LFM2-24B-A2B
02.24.2026ModelsLFM2-24B-A2B: Scaling Up the LFM2 Architecture
01.20.2026ModelsLFM2.5-1.2B-Thinking: On-Device Reasoning Under 1GB
01.07.2026ModelsThe Future of Meeting Summarization: Local, Fast, Private, and Fully Secure
01.05.2026ModelsIntroducing LFM2.5: The Next Generation of On-Device AI
10.28.2025ModelsLFM2-ColBERT-350M: One Model to Embed Them All
10.22.2025ProductHow Liquid AI Uses ExecuTorch to Power Efficient, Flexible On-Device Intelligence
10.22.2025ModelsLFM2-VL-3B: A New Efficient Vision-Language for the Edge
10.07.2025ModelsLFM2-8B-A1B: An Efficient On-device Mixture-of-Experts
10.01.2025ModelsLFM2-Audio: An End-to-End Audio Foundation Model
09.25.2025ModelsIntroducing Liquid Nanos — frontier‑grade performance on everyday devices
09.23.2025ModelsIntroducing LFM2-2.6B: Redefining Efficiency in Language Models
08.18.2025ProductFrom Cloud to Keyboard: LEAP Expands to Laptops with Cutting-Edge AMD Ryzen™ Power
08.12.2025ModelsLFM2-VL: Efficient Vision-Language Models
07.24.2025ProductLiquid <> .txt Collaboration
07.15.2025ProductLiquid AI Launches LEAP and Liquid Apollo: The Easiest Way to Build with On-Device AI
07.10.2025ModelsIntroducing LFM2: The Fastest On-Device Foundation Models on the Market
06.24.2025ModelsLFM-1B-Math: Can Small Models Be Concise Reasoners?
01.20.2025ModelsIntroducing LFM-7B: Setting New Standards for Efficient Language Models
09.30.2024ProductLiquid Foundation Models: Our First Series of Generative AI Models