yasserrmd/ jan-nano-4b

128 Downloads Updated 7 months ago

tools

ollama run yasserrmd/jan-nano-4b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "yasserrmd/jan-nano-4b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='yasserrmd/jan-nano-4b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'yasserrmd/jan-nano-4b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model yasserrmd/jan-nano-4b

Codex

Codex ollama launch codex --model yasserrmd/jan-nano-4b

OpenCode

OpenCode ollama launch opencode --model yasserrmd/jan-nano-4b

OpenClaw

OpenClaw ollama launch openclaw --model yasserrmd/jan-nano-4b

Models

Name

1 model

Size

Context

Input

jan-nano-4b:latest

2.4GB · 40K context window · Text · 7 months ago

jan-nano-4b:latest

2.4GB

40K

Text

Readme

🧠 Jan-Nano 4B

A quantized version of Jan-Nano 4B, designed for deep research tasks, autonomous tool use, and integration with the Model Context Protocol (MCP). This model is optimized for use with Ollama and supports local agentic workflows.

📦 Model Overview

Base: Qwen3 architecture
Size: 4B parameters (quantized)
Context Length: Up to 128K tokens
Specialty: Deep reasoning, tool-calling via MCP, compact size
Quantization: Q8 optimized for performance and compatibility

🚀 Quickstart with Ollama

1. Pull the Model

ollama pull yasserrmd/jan-nano-4b

2. Run the Model Locally

ollama run yasserrmd/jan-nano-4b

⚙️ Recommended Parameters

temperature: 0.7
top_p: 0.8
top_k: 20
min_p: 0.0
Optional: --hidethinking to suppress self-verbalization

Example:

ollama run yasserrmd/jan-nano-4b \
  --temperature 0.7 --top-p 0.8 --top-k 20 --hidethinking

📡 Features

✅ MCP tool-calling (search, summarize, calculator, etc.) ✅ Optimized for 128K token context length ✅ Suitable for research, question answering, and autonomous agents ✅ Fast inference on consumer GPUs (8–16GB VRAM)

📝 Example Usage

Prompt:

User: /no_think
How has AI improved weather forecasting in the last five years?

Model Output:

Automatically calls search tools via MCP
Synthesizes research into clear summaries
Provides references and statistics

🧩 Integrations

Can be used with external orchestration layers like LangGraph, Ollmcp, or custom HTTP MCP servers
Works well with tool templates and system prompts

📁 License & Source

Model: Menlo/Jan-nano on Hugging Face

# 🧠 Jan-Nano 4B

A quantized version of **Jan-Nano 4B**, designed for deep research tasks, autonomous tool use, and integration with the **Model Context Protocol (MCP)**. This model is optimized for use with [Ollama](https://ollama.com) and supports local agentic workflows.

---

## 📦 Model Overview

* **Base**: Qwen3 architecture
* **Size**: 4B parameters (quantized)
* **Context Length**: Up to 128K tokens
* **Specialty**: Deep reasoning, tool-calling via MCP, compact size
* **Quantization**: Q8 optimized for performance and compatibility

---

## 🚀 Quickstart with Ollama

### 1. Pull the Model

```bash
ollama pull yasserrmd/jan-nano-4b
```

### 2. Run the Model Locally

```bash
ollama run yasserrmd/jan-nano-4b
```

---

## ⚙️ Recommended Parameters

* `temperature`: `0.7`
* `top_p`: `0.8`
* `top_k`: `20`
* `min_p`: `0.0`
* Optional: `--hidethinking` to suppress self-verbalization

Example:

```bash
ollama run yasserrmd/jan-nano-4b \
  --temperature 0.7 --top-p 0.8 --top-k 20 --hidethinking
```

---

## 📡 Features

✅ MCP tool-calling (search, summarize, calculator, etc.)
✅ Optimized for 128K token context length
✅ Suitable for research, question answering, and autonomous agents
✅ Fast inference on consumer GPUs (8–16GB VRAM)

---

## 📝 Example Usage

**Prompt:**

```
User: /no_think
How has AI improved weather forecasting in the last five years?
```

**Model Output:**

* Automatically calls search tools via MCP
* Synthesizes research into clear summaries
* Provides references and statistics

---

## 🧩 Integrations

* Can be used with external orchestration layers like LangGraph, Ollmcp, or custom HTTP MCP servers
* Works well with tool templates and system prompts

---

## 📁 License & Source

* Model: [Menlo/Jan-nano on Hugging Face](https://huggingface.co/Menlo/Jan-nano)

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)