MacPaw partners with Liquid AI to deploy on-device AI models for Mac users.
News Hub
What actually shipped in agent engineering, pulled from the labs, arXiv and Hacker News.
See who we follow →LFM2.5-2.6B is a model for deploying agents across diverse environments.
Liquid AI describes a technique to expand and upgrade a model's tokenizer without retraining.
Liquid AI proposes Final Token Preference Optimization to reduce doom loops in language models.
Liquid AI released LFM2.5-230M, a model designed to run on diverse hardware platforms.
Liquid AI releases LFM2.5 Retrievers, bi-directional language foundation models for fast multilingual search.
Liquid AI releases LFM2.5-8B-A1B, an improved on-device mixture of experts model.
Liquid AI releases LFM2.5-VL-450M structured visual model for edge and cloud deployment.
LFM2.5-350M is a language model from Liquid AI.
LFM2-24B-A2B model runs tool-calling agents on consumer hardware without cloud infrastructure.
Liquid AI launched its largest LFM2 model for AI PCs alongside expanding partner ecosystem.
Liquid AI scaled up the LFM2 architecture to 24 billion parameters.
Liquid AI releases LFM2.5-1.2B-Thinking, a reasoning model under 1GB for on-device use.
LFM2.5 is next-generation on-device AI.
Liquid Labs defines frontier of intelligence through innovation.
Liquid AI advanced open science in AI with LFM2.
Liquid AI hosted Hack the Edge San Francisco event on edge-native AI acceleration.
Liquid AI partnered with Shopify to deploy sub-20ms foundation models for commerce.
Liquid AI released LFM2-ColBERT-350M, a unified embedding model for multiple tasks.
Liquid AI, AMD, and Robotec.ai demonstrated LFM2-VL-3B for embedded autonomous robotics applications.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.

