Blog Authors:

Published June 16, 2025

Jan-Nano: An Agentic Model

Note: Jan-Nano is a non-thinking model.

Overview

Jan-Nano is a compact 4-billion parameter language model specifically designed and trained for deep research tasks. This model has been optimized to work seamlessly with Model Context Protocol (MCP) servers, enabling efficient integration with various research tools and data sources.

Evaluation

Jan-Nano has been evaluated on the SimpleQA benchmark using our MCP-based benchmark methodology, demonstrating strong performance for its model size.

The evaluation was conducted using our MCP-based benchmark approach, which assesses the model’s performance on SimpleQA tasks while leveraging its native MCP server integration capabilities. This methodology better reflects Jan-Nano’s real-world performance as a tool-augmented research model, validating both its factual accuracy and its effectiveness in MCP-enabled environments.

How to Run Locally

Jan-Nano is currently supported by Jan, an open-source ChatGPT alternative that runs entirely on your computer. Jan provides a user-friendly interface for running local AI models with full privacy and control.

VLLM

Here is an example command you can use to run vllm with Jan-nano:

vllm serve Menlo/Jan-nano --host 0.0.0.0 --port 1234 --enable-auto-tool-choice --tool-call-parser hermes --chat-template ./qwen3_nonthinking.jinja

Recommended Sampling Parameters

• Temperature: 0.7
• Top-p: 0.8
• Top-k: 20
• Min-p: 0

Resources

Explore Jan-Nano and build upon our research:

• Model: Menlo/Jan-nano 
• Paper: Jan-nano Technical Report 
• Jan App: Open-source ChatGPT alternative that runs entirely on your computer

Citation

@misc{dao2025jannanotechnicalreport,
      title={Jan-nano Technical Report}, 
      author={Alan Dao and Dinh Bach Vu},
      year={2025},
      eprint={2506.22760},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2506.22760}, 
}