README.md

---
title: Mobile Chat Demo
emoji: 🚀
colorFrom: blue
colorTo: indigo
sdk: gradio
sdk_version: "4.44.0"
app_file: app.py
pinned: true
license: apache-2.0
tags:
  - mobile
  - llm
  - on-device
  - dispatchai
models:
  - dispatchAI/SmolLM2-135M-Instruct-mobile
---

# 🚀 dispatchAI Mobile Chat Demo

Chat with dispatchAI's mobile-optimized models directly in your browser. 

**Model:** SmolLM2-135M-Instruct-mobile — 135M parameters, under 500MB, designed to run on phones.

This Space runs on ZeroGPU (Team tier) so it stays responsive even under load.

## Try It

Just type a message and chat. The model is small but surprisingly capable for its size.

## Run This Model On Your Phone

```python
from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("dispatchAI/SmolLM2-135M-Instruct-mobile")
tokenizer = AutoTokenizer.from_pretrained("dispatchAI/SmolLM2-135M-Instruct-mobile")
```

Or with llama.cpp:
```bash
llama-cli -m model.gguf -p "Hello!" -n 100
```

## About dispatchAI

We re-engineer open-source LLMs for mobile and edge devices. 39 models, all tested on real Snapdragon hardware, all free.

🌐 [dispatchAI on HuggingFace](https://huggingface.co/dispatchAI)