VOOZH about

URL: https://huggingface.co/Menlo/Jan-nano-gguf

⇱ Menlo/Jan-nano-gguf · Hugging Face


Jan Nano

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

Authors: Alan Dao, Bach Vu Dinh

👁 image/png

Overview

Jan Nano is a fine-tuned language model built on top of the Qwen3 architecture. Developed as part of the Jan ecosystem, it balances compact size and extended context length, making it ideal for efficient, high-quality text generation in local or embedded environments.

Features

  • Tool Use: Excellent function calling and tool integration
  • Research: Enhanced research and information processing capabilities
  • Small Model: VRAM efficient for local deployment

Use it with Jan (UI)

  1. Install Jan using Quickstart

Original weight: https://huggingface.co/Menlo/Jan-nano

Recommended Sampling Parameters

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

📄 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}, 
}

Documentation

Setup, Usage & FAQ

Downloads last month
1,124
GGUF
Model size
4B params
Architecture
qwen3
Hardware compatibility
Log In to add your hardware

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for Menlo/Jan-nano-gguf

Finetuned
Qwen/Qwen3-4B
Finetuned
Menlo/Jan-nano
Quantized
(23)
this model

Collection including Menlo/Jan-nano-gguf

Paper for Menlo/Jan-nano-gguf