AI 服务暂时不可用，以下为来源正文，待恢复后补全翻译。
← Back to Text Models LFM2.5-2.6B is Liquid AI’s 2.6B dense model built for agentic workloads with a 128K context window and native tool calling. It runs on edge devices and it is trained to work reliably inside agent harnesses like Hermes Agent, OpenClaw, and Pi. HFGGUFMLXONNX Specifications PropertyValue Parameters2.6B Context Length128K tokens ArchitectureLFM2.5 (dense) Agentic & Tool Use Native tool calling, trained inside real agent harnesses 128K Context Long context for tool traces and multi-step workflows On-device Small enough to run on a laptop or phone Quick Start Transformers llama.cpp vLLM SGLang Was this page helpful? Suggest editsRaise issue ⌘I