Jan Nano

Authors: Alan Dao, Bach Vu Dinh, Thinh

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

Documentation

Setup, Usage & FAQ

Downloads last month
7,788
GGUF
Model size
4.02B params
Architecture
qwen3
Hardware compatibility
Log In to view the estimation

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 2 Ask for provider support

Model tree for Menlo/Jan-nano-gguf

Base model

Qwen/Qwen3-4B-Base
Finetuned
Qwen/Qwen3-4B
Finetuned
Menlo/Jan-nano
Quantized
(14)
this model

Collection including Menlo/Jan-nano-gguf