π Model Description
quantized_by: Menlo pipeline_tag: text-generation base_model: Menlo/Jan-nano basemodelrelation: quantized license: apache-2.0
Jan Nano
Note: Jan-Nano is a non-thinking model.Authors: Alan Dao, Bach Vu Dinh
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)
- 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
π 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 & FAQπ GGUF File List
| π Filename | π¦ Size | β‘ Download |
|---|---|---|
|
jan-nano-4b-Q3_K_L.gguf
LFS
Q3
|
2.09 GB | Download |
|
jan-nano-4b-Q3_K_M.gguf
LFS
Q3
|
1.93 GB | Download |
|
jan-nano-4b-Q3_K_S.gguf
LFS
Q3
|
1.76 GB | Download |
|
jan-nano-4b-Q4_0.gguf
Recommended
LFS
Q4
|
2.21 GB | Download |
|
jan-nano-4b-Q4_1.gguf
LFS
Q4
|
2.42 GB | Download |
|
jan-nano-4b-Q4_K_M.gguf
LFS
Q4
|
2.33 GB | Download |
|
jan-nano-4b-Q4_K_S.gguf
LFS
Q4
|
2.22 GB | Download |
|
jan-nano-4b-Q5_0.gguf
LFS
Q5
|
2.63 GB | Download |
|
jan-nano-4b-Q5_1.gguf
LFS
Q5
|
2.84 GB | Download |
|
jan-nano-4b-Q5_K_M.gguf
LFS
Q5
|
2.69 GB | Download |
|
jan-nano-4b-Q5_K_S.gguf
LFS
Q5
|
2.63 GB | Download |
|
jan-nano-4b-Q6_K.gguf
LFS
Q6
|
3.08 GB | Download |
|
jan-nano-4b-Q8_0.gguf
LFS
Q8
|
3.99 GB | Download |
|
jan-nano-4b-iQ4_XS.gguf
LFS
Q4
|
2.11 GB | Download |