Menlo/Jan-nano-128k

Menlo/Jan-nano-128k is a 4 billion parameter compact language model developed by Alan Dao and Bach Vu Dinh, designed for research applications. This model features a native 128k context window, enabling efficient processing of extensive documents and complex multi-turn conversations without typical performance degradation. It excels at deep document analysis and multi-document synthesis, making it suitable for research requiring complex reasoning over large information sets. Jan-nano-128k maintains compatibility with Model Context Protocol (MCP) servers and shows improved performance with longer contexts compared to its predecessor.