STORY · MODELLER_
LiquidAI launches LFM2.5-2.6B for local agents on any device
LiquidAI has launched LFM2.5-2.6B, a 2.6 billion parameter language model optimized for running intelligent agents directly on the user's device. The model supports tool calling and multi-step workflows while remaining small enough to run on laptops, phones, and CPU-based hardware, with inference speeds up to 220 tokens per second on Apple M5 Max.
WHY IT MATTERS
This enables developers to deploy agent-based applications entirely locally without cloud services, reducing costs and preserving data privacy. The model performs competitively against models that are four times larger on agentic tasks.
SOURCES
MACHINE-GENERATED SUMMARY This summary is written by machine from the sources below. We sort and explain — but we are a way into the field, not the final word. Check the source when something matters to you.