5 models
Fast 2.6B local AI agent with thinking that rivals models 4x larger on tool use and multi-step agentic tasks.
LFM2.5-2.6B by Liquid AI — deploy agents everywhere. A 2.6B dense reasoning model (Q4_K_M, ~1.7 GB) with native tool calling, 128K context, and 16-language support. Runs on any 8 GB GPU.
LFM2.5-2.6B By LiquidAI
Local English proofreading for the Proofer Chrome and Brave extension, using a Q4_K_M fine-tune of LFM2.5-2.6B.