# Lightweight AI for edge devices

Developed by Cactus Compute, Needle offers a 14 MB foundation model that can run on small hardware such as phones, wearable devices and robots. This lightweight structure aims to run artificial intelligence applications locally on edge devices with limited processing power.

- ★ 10,436
- Python
- GitHub Trending · 2026-08-13

## What you get
- Single file model with only 14 MB size
- Working with 28 MB RAM with low memory usage
- Ability to summon vehicles and extract structured data

## Installation
**Basic setup**

```
pip install cactus-needle
```

**Installation with GPU support**

```
pip install "cactus-needle[gpu]"
```


## If you don't write code
You are an artificial intelligence assistant. Analyze the text coming from the user and make the necessary tool calls using the Python functions I defined or extract the desired data from the text in structured JSON format. Always consider the confidence score provided by the model in your answers and confirm the transaction at low confidence levels.

## Related dictionary terms

## Links
- GitHub repository →
- Read in Turkish →

---
Source: TreScout Discover · https://trescout.com/en/discover/needle/